diff --git a/.gitignore b/.gitignore
index b6a361a..8c70132 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,5 +1,7 @@
 *.DS_Store
 
+*.history
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
diff --git a/bemb/__init__.py b/bemb/__init__.py
index 9822e51..b84e76b 100644
--- a/bemb/__init__.py
+++ b/bemb/__init__.py
@@ -1,3 +1,6 @@
-__version__ = '0.1.4'
+__version__ = '0.1.7'
 import bemb.model
 import bemb.utils
+import bemb.data
+
+from .utils.run_helper_lightning import run
diff --git a/bemb/data/__init__.py b/bemb/data/__init__.py
new file mode 100644
index 0000000..d1d69ae
--- /dev/null
+++ b/bemb/data/__init__.py
@@ -0,0 +1 @@
+from .simulate_choice_dataset import load_simulation_dataset
\ No newline at end of file
diff --git a/bemb/data/simulate_choice_dataset.py b/bemb/data/simulate_choice_dataset.py
new file mode 100644
index 0000000..3731a0d
--- /dev/null
+++ b/bemb/data/simulate_choice_dataset.py
@@ -0,0 +1,42 @@
+"""
+Generate a simulated choice dataset for tutorials, unit tests, and debugging.
+"""
+from typing import List
+
+import numpy as np
+import torch
+from torch_choice.data import ChoiceDataset
+
+
+def load_simulation_dataset(num_users: int, num_items: int, data_size: int) -> List[ChoiceDataset]:
+    user_index = torch.LongTensor(np.random.choice(num_users, size=data_size))
+    Us = np.arange(num_users)
+    Is = np.sin(np.arange(num_users) / num_users * 4 * np.pi)
+    Is = (Is + 1) / 2 * num_items
+    Is = Is.astype(int)
+
+    PREFERENCE = dict((u, i) for (u, i) in zip(Us, Is))
+
+    # construct users.
+    item_index = torch.LongTensor(np.random.choice(num_items, size=data_size))
+
+    for idx in range(data_size):
+        if np.random.rand() <= 0.5:
+            item_index[idx] = PREFERENCE[int(user_index[idx])]
+
+    user_obs = torch.zeros(num_users, num_items)
+    user_obs[torch.arange(num_users), Is] = 1
+
+    item_obs = torch.eye(num_items)
+
+    dataset = ChoiceDataset(user_index=user_index, item_index=item_index, user_obs=user_obs, item_obs=item_obs)
+
+    idx = np.random.permutation(len(dataset))
+    train_size = int(0.8 * len(dataset))
+    val_size = int(0.1 * len(dataset))
+    train_idx = idx[:train_size]
+    val_idx = idx[train_size: train_size + val_size]
+    test_idx = idx[train_size + val_size:]
+
+    dataset_list = [dataset[train_idx], dataset[val_idx], dataset[test_idx]]
+    return dataset_list
diff --git a/bemb/model/bayesian_coefficient.py b/bemb/model/bayesian_coefficient.py
index 790c4fe..464c95a 100644
--- a/bemb/model/bayesian_coefficient.py
+++ b/bemb/model/bayesian_coefficient.py
@@ -6,9 +6,11 @@
 """
 from typing import Optional, Tuple, Union
 
+import numpy as np
 import torch
 import torch.nn as nn
 from torch.distributions.lowrank_multivariate_normal import LowRankMultivariateNormal
+from torch.distributions.gamma import Gamma
 
 
 class BayesianCoefficient(nn.Module):
@@ -21,7 +23,8 @@ def __init__(self,
                  num_obs: Optional[int] = None,
                  dim: int = 1,
                  prior_mean: float = 0.0,
-                 prior_variance: Union[float, torch.Tensor] = 1.0
+                 prior_variance: Union[float, torch.Tensor] = 1.0,
+                 distribution: str = 'gaussian'
                  ) -> None:
         """The Bayesian coefficient object represents a learnable tensor mu_i in R^k, where i is from a family (e.g., user, item)
             so there are num_classes * num_obs learnable weights in total.
@@ -63,12 +66,34 @@ def __init__(self,
                 If a tensor with shape (num_classes, dim) is supplied, supplying a (num_classes, dim) tensor is amount
                 to specifying a different prior variance for each entry in the coefficient.
                 Defaults to 1.0.
+            distribution (str, optional): the distribution of the coefficient. Currently we support 'gaussian' and 'gamma'.
+                Defaults to 'gaussian'.
         """
         super(BayesianCoefficient, self).__init__()
         # do we use this at all? TODO: drop self.variation.
         assert variation in ['item', 'user', 'constant', 'category']
 
         self.variation = variation
+
+        assert distribution in ['gaussian', 'gamma'], f'Unsupported distribution {distribution}'
+        if distribution == 'gamma':
+            '''
+            assert not obs2prior, 'Gamma distribution is not supported for obs2prior at present.'
+            mean = 1.0
+            variance = 10.0
+            assert mean > 0, 'Gamma distribution requires mean > 0'
+            assert variance > 0, 'Gamma distribution requires variance > 0'
+            # shape (concentration) is mean^2/variance, rate is variance/mean for Gamma distribution.
+            shape = prior_mean ** 2 / prior_variance
+            rate = prior_mean / prior_variance
+            prior_mean = np.log(shape)
+            prior_variance = rate
+            '''
+            prior_mean = np.log(prior_mean)
+            prior_variance = prior_variance
+
+        self.distribution = distribution
+
         self.obs2prior = obs2prior
         if variation == 'constant' or variation == 'category':
             if obs2prior:
@@ -89,13 +114,15 @@ def __init__(self,
         if self.obs2prior:
             # the mean of prior distribution depends on observables.
             # initiate a Bayesian Coefficient with shape (dim, num_obs) standard Gaussian.
+            prior_H_dist = 'gaussian'
             self.prior_H = BayesianCoefficient(variation='constant',
                                                num_classes=dim,
                                                obs2prior=False,
                                                dim=num_obs,
                                                prior_variance=1.0,
                                                H_zero_mask=self.H_zero_mask,
-                                               is_H=True)  # this is a distribution responsible for the obs2prior H term.
+                                               is_H=True,
+                                               distribution=prior_H_dist)  # this is a distribution responsible for the obs2prior H term.
 
         else:
             self.register_buffer(
@@ -114,13 +141,21 @@ def __init__(self,
             num_classes, dim) * self.prior_variance)
 
         # create variational distribution.
-        self.variational_mean_flexible = nn.Parameter(
-            torch.randn(num_classes, dim), requires_grad=True)
+        if self.distribution == 'gaussian':
+            self.variational_mean_flexible = nn.Parameter(
+                torch.randn(num_classes, dim), requires_grad=True)
+        # TOOD(kanodiaayush): initialize the gamma distribution variational mean in a more principled way.
+        elif self.distribution == 'gamma':
+            # initialize using uniform distribution between 0.5 and 1.5
+            # for a gamma distribution, we store the concentration as log(concentration) = variational_mean_flexible
+            self.variational_mean_flexible = nn.Parameter(
+                torch.rand(num_classes, dim) + 0.5, requires_grad=True)
 
         if self.is_H and self.H_zero_mask is not None:
             assert self.H_zero_mask.shape == self.variational_mean_flexible.shape, \
                 f"The H_zero_mask should have exactly the shape as the H variable, `H_zero_mask`.shape is {self.H_zero_mask.shape}, `H`.shape is {self.variational_mean_flexible.shape} "
 
+        # for gamma distribution, we store the rate as log(rate) = variational_logstd
         self.variational_logstd = nn.Parameter(
             torch.randn(num_classes, dim), requires_grad=True)
 
@@ -163,6 +198,10 @@ def variational_mean(self) -> torch.Tensor:
         else:
             M = self.variational_mean_fixed + self.variational_mean_flexible
 
+        if self.distribution == 'gamma':
+            # M = torch.pow(M, 2) + 0.000001
+            M = M.exp() / self.variational_logstd.exp()
+
         if self.is_H and (self.H_zero_mask is not None):
             # a H-variable with zero-entry restriction.
             # multiply zeros to entries with H_zero_mask[i, j] = 1.
@@ -196,7 +235,11 @@ def log_prior(self,
         Returns:
             torch.Tensor: the log prior of the variable with shape (num_seeds, num_classes).
         """
-        # p(sample)
+        # DEBUG_MARKER
+        '''
+        print(sample)
+        print('log_prior')
+        '''
         num_seeds, num_classes, dim = sample.shape
         # shape (num_seeds, num_classes)
         if self.obs2prior:
@@ -211,9 +254,19 @@ def log_prior(self,
 
         else:
             mu = self.prior_zero_mean
-        out = LowRankMultivariateNormal(loc=mu,
-                                        cov_factor=self.prior_cov_factor,
-                                        cov_diag=self.prior_cov_diag).log_prob(sample)
+
+        if self.distribution == 'gaussian':
+            out = LowRankMultivariateNormal(loc=mu,
+                                            cov_factor=self.prior_cov_factor,
+                                            cov_diag=self.prior_cov_diag).log_prob(sample)
+        elif self.distribution == 'gamma':
+            concentration = torch.exp(mu)
+            rate = self.prior_variance
+            out = Gamma(concentration=concentration,
+                        rate=rate).log_prob(sample)
+            # sum over the last dimension
+            out = torch.sum(out, dim=-1)
+
         assert out.shape == (num_seeds, num_classes)
         return out
 
@@ -250,6 +303,7 @@ def rsample(self, num_seeds: int = 1) -> Union[torch.Tensor, Tuple[torch.Tensor]
         """
         value_sample = self.variational_distribution.rsample(
             torch.Size([num_seeds]))
+        # DEBUG_MARKER
         if self.obs2prior:
             # sample obs2prior H as well.
             H_sample = self.prior_H.rsample(num_seeds=num_seeds)
@@ -258,12 +312,22 @@ def rsample(self, num_seeds: int = 1) -> Union[torch.Tensor, Tuple[torch.Tensor]
             return value_sample
 
     @property
-    def variational_distribution(self) -> LowRankMultivariateNormal:
+    def variational_distribution(self) -> Union[LowRankMultivariateNormal, Gamma]:
         """Constructs the current variational distribution of the coefficient from current variational mean and covariance.
         """
-        return LowRankMultivariateNormal(loc=self.variational_mean,
-                                         cov_factor=self.variational_cov_factor,
-                                         cov_diag=torch.exp(self.variational_logstd))
+        if self.distribution == 'gaussian':
+            return LowRankMultivariateNormal(loc=self.variational_mean,
+                                             cov_factor=self.variational_cov_factor,
+                                             cov_diag=torch.exp(self.variational_logstd))
+        elif self.distribution == 'gamma':
+            # for a gamma distribution, we store the concentration as log(concentration) = variational_mean_flexible
+            assert self.variational_mean_fixed == None, 'Gamma distribution does not support fixed mean'
+            concentration = self.variational_mean_flexible.exp()
+            # for gamma distribution, we store the rate as log(rate) = variational_logstd
+            rate = torch.exp(self.variational_logstd)
+            return Gamma(concentration=concentration, rate=rate)
+        else:
+            raise NotImplementedError("Unknown variational distribution type.")
 
     @property
     def device(self) -> torch.device:
diff --git a/bemb/model/bemb.py b/bemb/model/bemb.py
index 59eadd8..fd7fbe3 100644
--- a/bemb/model/bemb.py
+++ b/bemb/model/bemb.py
@@ -39,25 +39,41 @@ def parse_utility(utility_string: str) -> List[Dict[str, Union[List[str], None]]
     A helper function parse utility string into a list of additive terms.
 
     Example:
-        utility_string = 'lambda_item + theta_user * alpha_item + gamma_user * beta_item * price_obs'
+        utility_string = 'lambda_item + theta_user * alpha_item - gamma_user * beta_item * price_obs'
         output = [
             {
                 'coefficient': ['lambda_item'],
-                'observable': None
+                'observable': None,
+                'sign': 1.0,
+
             },
             {
                 'coefficient': ['theta_user', 'alpha_item'],
                 'observable': None
+                'sign': 1.0,
             },
             {
                 'coefficient': ['gamma_user', 'beta_item'],
                 'observable': 'price_obs'
+                'sign': -1.0,
             }
             ]
+         Note that 'minus' is allowed in the utility string. If the first term is negative, the minus should be without a space.
     """
     # split additive terms
     coefficient_suffix = ('_item', '_user', '_constant', '_category')
-    observable_prefix = ('item_', 'user_', 'session_', 'price_', 'taste_')
+    observable_prefix = ('item_', 'user_', 'session_',
+                         # (user, item)-specific.
+                         'useritem_', 'itemuser_', 'taste_',
+                         # (user, session)-specific.
+                         'usersession', 'sessionuser',
+                         # (session, item)-specific.
+                         'itemsession_', 'sessionitem_', 'price_',
+                         # (user, session, item)-specific.
+                         'usersessionitem_', 'useritemsession_',
+                         'sessionuseritem_', 'sessionitemuser_',
+                         'itemusersession_', 'itemsessionuser_',
+                         )
 
     def is_coefficient(name: str) -> bool:
         return any(name.endswith(suffix) for suffix in coefficient_suffix)
@@ -65,24 +81,25 @@ def is_coefficient(name: str) -> bool:
     def is_observable(name: str) -> bool:
         return any(name.startswith(prefix) for prefix in observable_prefix)
 
+    utility_string = utility_string.replace(' - ', ' + -')
     additive_terms = utility_string.split(' + ')
     additive_decomposition = list()
     for term in additive_terms:
-        atom = {'coefficient': [], 'observable': None}
+        if term.startswith('-'):
+            sign = -1.0
+            term = term[1:]
+        else:
+            sign = 1.0
+        atom = {'coefficient': [], 'observable': None, 'sign': sign}
         # split multiplicative terms.
         for x in term.split(' * '):
-            # Programmers can specify itemsession for price observables, this brings better intuition.
-            if x.startswith('itemsession_'):
-                # case 1: special observable name.
-                atom['observable'] = 'price_' + x[len('itemsession_'):]
-            elif is_observable(x):
-                # case 2: normal observable name.
+            assert not (is_observable(x) and is_coefficient(x)), f"The element {x} is ambiguous, it follows naming convention of both an observable and a coefficient."
+            if is_observable(x):
                 atom['observable'] = x
             elif is_coefficient(x):
-                # case 3: normal coefficient name.
                 atom['coefficient'].append(x)
             else:
-                # case 4: special coefficient name.
+                # case 3: special coefficient name.
                 # the _constant coefficient suffix is not intuitive enough, we allow none coefficient suffix for
                 # coefficient with constant value. For example, `lambda` is the same as `lambda_constant`.
                 warnings.warn(f'{x} term has no appropriate coefficient suffix or observable prefix, it is assumed to be a coefficient constant across all items, users, and sessions. If this is the desired behavior, you can also specify `{x}_constant` in the utility formula to avoid this warning message. The utility parser has replaced {x} term with `{x}_constant`.')
@@ -107,6 +124,7 @@ def __init__(self,
                  num_items: int,
                  pred_item: bool,
                  num_classes: int = 2,
+                 coef_dist_dict: Dict[str, str] = {'default' : 'gaussian'},
                  H_zero_mask_dict: Optional[Dict[str, torch.BoolTensor]] = None,
                  prior_mean: Union[float, Dict[str, float]] = 0.0,
                  prior_variance: Union[float, Dict[str, float]] = 1.0,
@@ -134,6 +152,14 @@ def __init__(self,
                     lambda_item + theta_user * alpha_item + gamma_user * beta_item * price_obs
                 See the doc-string of parse_utility for an example.
 
+            coef_dist_dict (Dict[str, str]): a dictionary mapping coefficient name to coefficient distribution name.
+                The coefficient distribution name can be one of the following:
+                1. 'gaussian'
+                2. 'gamma' - obs2prior is not supported for gamma coefficients
+                If a coefficient does not appear in the dictionary, it will be assigned the distribution specified
+                by the 'default' key. By default, the default distribution is 'gaussian'.
+                For coefficients which have gamma distributions, prior mean and variance MUST be specified in the prior_mean and prior_variance arguments if obs2prior is False for this coefficient. If obs2prior is True, prior_variance is still required
+
             obs2prior_dict (Dict[str, bool]): a dictionary maps coefficient name (e.g., 'lambda_item')
                 to a boolean indicating if observable (e.g., item_obs) enters the prior of the coefficient.
 
@@ -178,6 +204,8 @@ def __init__(self,
                 If no `prior_mean['default']` is provided, the default prior mean will be 0.0 for those coefficients
                 not in the prior_mean.keys().
 
+                For coefficients with gamma distributions, prior_mean specifies the shape parameter of the gamma prior.
+
                 Defaults to 0.0.
 
             prior_variance (Union[float, Dict[str, float]], Dict[str, torch. Tensor]): the variance of prior distribution
@@ -197,6 +225,8 @@ def __init__(self,
                 If no `prior_variance['default']` is provided, the default prior variance will be 1.0 for those coefficients
                 not in the prior_variance.keys().
 
+                For coefficients with gamma distributions, prior_variance specifies the concentration parameter of the gamma prior.
+
                 Defaults to 1.0, which means all priors have identity matrix as the covariance matrix.
 
             num_users (int, optional): number of users, required only if coefficient or observable
@@ -219,12 +249,15 @@ def __init__(self,
                 user and item observables can enter the prior of coefficient. Hence session, price,
                 and taste observables are never required, we include it here for completeness.
 
-            deterministic_variational (bool, optional): if True, the variational posterior is equivalent to frequentist MLE estimates of parameters
+            deterministic_variational (bool, optional): if True, the variational posterior is equivalent to frequentist MLE estimates of parameters.
+                Note that this is equivalent to having a point mass with zero variance for the variational posterior.
+                Defaults to False.
         """
         super(BEMBFlex, self).__init__()
         self.utility_formula = utility_formula
         self.obs2prior_dict = obs2prior_dict
         self.coef_dim_dict = coef_dim_dict
+        self.coef_dist_dict = coef_dist_dict
         if H_zero_mask_dict is not None:
             self.H_zero_mask_dict = H_zero_mask_dict
         else:
@@ -301,9 +334,6 @@ def __init__(self,
             'user': num_user_obs,
             'item': num_item_obs,
             'category' : 0,
-            'session': num_session_obs,
-            'price': num_price_obs,
-            'taste': num_taste_obs,
             'constant': 1  # not really used, for dummy variables.
         }
 
@@ -320,16 +350,30 @@ def __init__(self,
         for additive_term in self.formula:
             for coef_name in additive_term['coefficient']:
                 variation = coef_name.split('_')[-1]
+
+                if coef_name not in self.coef_dist_dict.keys():
+                    if 'default' in self.coef_dist_dict.keys():
+                        self.coef_dist_dict[coef_name] = self.coef_dist_dict['default']
+                    else:
+                        warnings.warn(f"You provided a dictionary of coef_dist_dict, but coefficient {coef_name} is not a key in it. Supply a value for 'default' in the coef_dist_dict dictionary to use that as default value (e.g., coef_dist_dict['default'] = 'gaussian'); now using distribution='gaussian' since this is not supplied.")
+                        self.coef_dist_dict[coef_name] = 'gaussian'
+
+                elif self.coef_dist_dict[coef_name] == 'gamma':
+                    if not self.obs2prior_dict[coef_name]:
+                        assert isinstance(self.prior_mean, dict) and coef_name in self.prior_mean.keys(), \
+                            f"Prior mean for {coef_name} needs to be provided because it's posterior is estimated as a gamma distribution."
+                        assert isinstance(self.prior_variance, dict) and coef_name in self.prior_variance.keys(), \
+                            f"Prior variance for {coef_name} needs to be provided because it's posterior is estimated as a gamma distribution."
+
                 if isinstance(self.prior_mean, dict):
                     # the user didn't specify prior mean for this coefficient.
                     if coef_name not in self.prior_mean.keys():
                         # the user may specify 'default' prior variance through the prior_variance dictionary.
                         if 'default' in self.prior_mean.keys():
-                            # warnings.warn(f"You provided a dictionary of prior mean, but coefficient {coef_name} is not a key in it. We found a key 'default' in the dictionary, so we use the value of 'default' as the prior mean for coefficient {coef_name}.")
                             self.prior_mean[coef_name] = self.prior_mean['default']
                         else:
-                            # warnings.warn(f"You provided a dictionary of prior mean, but coefficient {coef_name} is not a key in it. Supply a value for 'default' in the prior_mean dictionary to use that as default value (e.g., prior_mean['default'] = 0.1); now using mean=0.0 since this is not supplied.")
-                            self.prior_variance[coef_name] = 0.0
+                            warnings.warn(f"You provided a dictionary of prior mean, but coefficient {coef_name} is not a key in it. Supply a value for 'default' in the prior_mean dictionary to use that as default value (e.g., prior_mean['default'] = 0.1); now using mean=0.0 since this is not supplied.")
+                            self.prior_mean[coef_name] = 0.0
 
                 mean = self.prior_mean[coef_name] if isinstance(
                     self.prior_mean, dict) else self.prior_mean
@@ -339,7 +383,6 @@ def __init__(self,
                     if coef_name not in self.prior_variance.keys():
                         # the user may specify 'default' prior variance through the prior_variance dictionary.
                         if 'default' in self.prior_variance.keys():
-                            # warnings.warn(f"You provided a dictionary of prior variance, but coefficient {coef_name} is not a key in it. We found a key 'default' in the dictionary, so we use the value of 'default' as the prior variance for coefficient {coef_name}.")
                             self.prior_variance[coef_name] = self.prior_variance['default']
                         else:
                             # warnings.warn(f"You provided a dictionary of prior variance, but coefficient {coef_name} is not a key in it. Supply a value for 'default' in the prior_variance dictionary to use that as default value (e.g., prior_variance['default'] = 0.3); now using variance=1.0 since this is not supplied.")
@@ -364,7 +407,8 @@ def __init__(self,
                                                            prior_mean=mean,
                                                            prior_variance=s2,
                                                            H_zero_mask=H_zero_mask,
-                                                           is_H=False)
+                                                           is_H=False,
+                                                           distribution=self.coef_dist_dict[coef_name])
         self.coef_dict = nn.ModuleDict(coef_dict)
 
         # ==============================================================================================================
@@ -571,7 +615,9 @@ def forward(self, batch: ChoiceDataset,
             'item_index', 'all_items'], "return_scope must be either 'item_index' or 'all_items'."
         assert deterministic in [True, False]
         if (not deterministic) and (sample_dict is None):
-            assert num_seeds >= 1, "A positive interger `num_seeds` is required if `deterministic` is False and no `sample_dict` is provided."
+            if num_seeds is None:
+                raise ValueError("A positive integer `num_seeds` is required if `deterministic` is False and no `sample_dict` is provided.")
+            assert num_seeds >= 1, "A positive integer `num_seeds` is required if `deterministic` is False and no `sample_dict` is provided."
 
         # when pred_item is true, the model is predicting which item is bought (specified by item_index).
         if self.pred_item:
@@ -585,10 +631,7 @@ def forward(self, batch: ChoiceDataset,
             # Use the means of variational distributions as the sole deterministic MC sample.
             # NOTE: here we don't need to sample the obs2prior weight H since we only compute the log-likelihood.
             # TODO: is this correct?
-            sample_dict = dict()
-            for coef_name, coef in self.coef_dict.items():
-                sample_dict[coef_name] = coef.variational_distribution.mean.unsqueeze(
-                    dim=0)  # (1, num_*, dim)
+            sample_dict = self.sample_coefficient_dictionary(num_seeds, deterministic=True)
         else:
             if sample_dict is None:
                 # sample stochastic parameters.
@@ -637,11 +680,12 @@ def device(self) -> torch.device:
     # ==================================================================================================================
     # helper functions.
     # ==================================================================================================================
-    def sample_coefficient_dictionary(self, num_seeds: int) -> Dict[str, torch.Tensor]:
+    def sample_coefficient_dictionary(self, num_seeds: int, deterministic: bool = False) -> Dict[str, torch.Tensor]:
         """A helper function to sample parameters from coefficients.
 
         Args:
             num_seeds (int): number of random samples.
+            deterministic (bool, optional): whether to use the mean of variational distributions as the sole sample.
 
         Returns:
             Dict[str, torch.Tensor]: a dictionary maps coefficient names to tensor of sampled coefficient parameters,
@@ -650,16 +694,21 @@ def sample_coefficient_dictionary(self, num_seeds: int) -> Dict[str, torch.Tenso
         """
         sample_dict = dict()
         for coef_name, coef in self.coef_dict.items():
-            s = coef.rsample(num_seeds)
-            if coef.obs2prior:
-                # sample both obs2prior weight and realization of variable.
-                assert isinstance(s, tuple) and len(s) == 2
-                sample_dict[coef_name] = s[0]
-                sample_dict[coef_name + '.H'] = s[1]
+            if deterministic:
+                sample_dict[coef_name] = coef.variational_distribution.mean.unsqueeze(dim=0)  # (1, num_*, dim)
+                if coef.obs2prior:
+                    sample_dict[coef_name + '.H'] = coef.prior_H.variational_distribution.mean.unsqueeze(dim=0)  # (1, num_*, dim)
             else:
-                # only sample the realization of variable.
-                assert torch.is_tensor(s)
-                sample_dict[coef_name] = s
+                s = coef.rsample(num_seeds)
+                if coef.obs2prior:
+                    # sample both obs2prior weight and realization of variable.
+                    assert isinstance(s, tuple) and len(s) == 2
+                    sample_dict[coef_name] = s[0]
+                    sample_dict[coef_name + '.H'] = s[1]
+                else:
+                    # only sample the realization of variable.
+                    assert torch.is_tensor(s)
+                    sample_dict[coef_name] = s
         return sample_dict
 
     @torch.no_grad()
@@ -848,25 +897,35 @@ def reshape_observable(obs, name):
             # samples of coefficients.
             O = obs.shape[-1]  # number of observables.
             assert O == positive_integer
-            if name.startswith('item_'):
+            if batch._is_item_attribute(name):
                 assert obs.shape == (I, O)
                 obs = obs.view(1, 1, I, O).expand(R, P, -1, -1)
-            elif name.startswith('user_'):
+            elif batch._is_user_attribute(name):
                 assert obs.shape == (U, O)
                 obs = obs[user_index, :]  # (P, O)
                 obs = obs.view(1, P, 1, O).expand(R, -1, I, -1)
-            elif name.startswith('session_'):
+            elif batch._is_session_attribute(name):
                 assert obs.shape == (S, O)
                 obs = obs[session_index, :]  # (P, O)
-                return obs.view(1, P, 1, O).expand(R, -1, I, -1)
-            elif name.startswith('price_'):
+                obs = obs.view(1, P, 1, O).expand(R, -1, I, -1)
+            elif batch._is_price_attribute(name):
                 assert obs.shape == (S, I, O)
                 obs = obs[session_index, :, :]  # (P, I, O)
-                return obs.view(1, P, I, O).expand(R, -1, -1, -1)
-            elif name.startswith('taste_'):
+                obs = obs.view(1, P, I, O).expand(R, -1, -1, -1)
+            elif batch._is_useritem_attribute(name):
                 assert obs.shape == (U, I, O)
                 obs = obs[user_index, :, :]  # (P, I, O)
-                return obs.view(1, P, I, O).expand(R, -1, -1, -1)
+                obs = obs.view(1, P, I, O).expand(R, -1, -1, -1)
+            elif batch._is_usersession_attribute(name):
+                assert obs.shape == (U, S, O)
+                obs = obs[user_index, session_index, :]  # (P, O)
+                assert obs.shape == (P, O)
+                obs = obs.view(1, P, 1, O).expand(R, -1, I, -1)
+            elif batch._is_usersessionitem_attribute(name):
+                assert obs.shape == (U, S, I, O)
+                obs = obs[user_index, session_index, :, :]  # (P, I, O)
+                assert obs.shape == (P, I, O)
+                obs = obs.view(1, P, I, O).expand(R, -1, -1, -1)
             else:
                 raise ValueError
             assert obs.shape == (R, P, I, O)
@@ -889,6 +948,7 @@ def reshape_observable(obs, name):
                     sample_dict[coef_name], coef_name)
                 assert coef_sample.shape == (R, P, I, 1)
                 additive_term = coef_sample.view(R, P, I)
+                additive_term *= term['sign']
 
             # Type II: factorized coefficient, e.g., <theta_user, lambda_item>.
             elif len(term['coefficient']) == 2 and term['observable'] is None:
@@ -904,6 +964,7 @@ def reshape_observable(obs, name):
                     R, P, I, positive_integer)
 
                 additive_term = (coef_sample_0 * coef_sample_1).sum(dim=-1)
+                additive_term *= term['sign']
 
             # Type III: single coefficient multiplied by observable, e.g., theta_user * x_obs_item.
             elif len(term['coefficient']) == 1 and term['observable'] is not None:
@@ -917,6 +978,7 @@ def reshape_observable(obs, name):
                 assert obs.shape == (R, P, I, positive_integer)
 
                 additive_term = (coef_sample * obs).sum(dim=-1)
+                additive_term *= term['sign']
 
             # Type IV: factorized coefficient multiplied by observable.
             # e.g., gamma_user * beta_item * price_obs.
@@ -947,6 +1009,7 @@ def reshape_observable(obs, name):
                 coef = (coef_sample_0 * coef_sample_1).sum(dim=-1)
 
                 additive_term = (coef * obs).sum(dim=-1)
+                additive_term *= term['sign']
 
             else:
                 raise ValueError(f'Undefined term type: {term}')
@@ -957,7 +1020,6 @@ def reshape_observable(obs, name):
         # ==============================================================================================================
         # Mask Out Unavailable Items in Each Session.
         # ==============================================================================================================
-
         if batch.item_availability is not None:
             # expand to the Monte Carlo sample dimension.
             # (S, I) -> (P, I) -> (1, P, I) -> (R, P, I)
@@ -1052,6 +1114,8 @@ def log_likelihood_item_index(self, batch: ChoiceDataset, return_logit: bool, sa
         U = self.num_users
         I = self.num_items
         NC = self.num_categories
+
+        assert len(user_index) == len(session_index) == len(relevant_item_index) == total_computation
         # ==========================================================================================
         # Helper Functions for Reshaping.
         # ==========================================================================================
@@ -1078,21 +1142,27 @@ def reshape_observable(obs, name):
             # samples of coefficients.
             O = obs.shape[-1]  # number of observables.
             assert O == positive_integer
-            if name.startswith('item_'):
+            if batch._is_item_attribute(name):
                 assert obs.shape == (I, O)
                 obs = obs[relevant_item_index, :]
-            elif name.startswith('user_'):
+            elif batch._is_user_attribute(name):
                 assert obs.shape == (U, O)
                 obs = obs[user_index, :]
-            elif name.startswith('session_'):
+            elif batch._is_session_attribute(name):
                 assert obs.shape == (S, O)
                 obs = obs[session_index, :]
-            elif name.startswith('price_'):
+            elif batch._is_price_attribute(name):
                 assert obs.shape == (S, I, O)
                 obs = obs[session_index, relevant_item_index, :]
-            elif name.startswith('taste_'):
+            elif batch._is_useritem_attribute(name):
                 assert obs.shape == (U, I, O)
                 obs = obs[user_index, relevant_item_index, :]
+            elif batch._is_usersession_attribute(name):
+                assert obs.shape == (U, S, O)
+                obs = obs[user_index, session_index, :]  # (total_computation, O)
+            elif batch._is_usersessionitem_attribute(name):
+                assert obs.shape == (U, S, I, O)
+                obs = obs[user_index, session_index, relevant_item_index, :]
             else:
                 raise ValueError
             assert obs.shape == (total_computation, O)
@@ -1113,6 +1183,7 @@ def reshape_observable(obs, name):
                     sample_dict[coef_name], coef_name)
                 assert coef_sample.shape == (R, total_computation, 1)
                 additive_term = coef_sample.view(R, total_computation)
+                additive_term *= term['sign']
 
             # Type II: factorized coefficient, e.g., <theta_user, lambda_item>.
             elif len(term['coefficient']) == 2 and term['observable'] is None:
@@ -1128,6 +1199,7 @@ def reshape_observable(obs, name):
                     R, total_computation, positive_integer)
 
                 additive_term = (coef_sample_0 * coef_sample_1).sum(dim=-1)
+                additive_term *= term['sign']
 
             # Type III: single coefficient multiplied by observable, e.g., theta_user * x_obs_item.
             elif len(term['coefficient']) == 1 and term['observable'] is not None:
@@ -1142,6 +1214,7 @@ def reshape_observable(obs, name):
                 assert obs.shape == (R, total_computation, positive_integer)
 
                 additive_term = (coef_sample * obs).sum(dim=-1)
+                additive_term *= term['sign']
 
             # Type IV: factorized coefficient multiplied by observable.
             # e.g., gamma_user * beta_item * price_obs.
@@ -1171,6 +1244,7 @@ def reshape_observable(obs, name):
                 coef = (coef_sample_0 * coef_sample_1).sum(dim=-1)
 
                 additive_term = (coef * obs).sum(dim=-1)
+                additive_term *= term['sign']
 
             else:
                 raise ValueError(f'Undefined term type: {term}')
@@ -1302,7 +1376,7 @@ def log_variational(self, sample_dict: Dict[str, torch.Tensor]) -> torch.Tensor:
         return total
 
     def elbo(self, batch: ChoiceDataset, num_seeds: int = 1) -> torch.Tensor:
-        """A combined method to computes the current ELBO given a batch, this method is used for training the model.
+        """A combined method to compute the current ELBO given a batch, this method is used for training the model.
 
         Args:
             batch (ChoiceDataset): a ChoiceDataset containing necessary information.
@@ -1316,17 +1390,7 @@ def elbo(self, batch: ChoiceDataset, num_seeds: int = 1) -> torch.Tensor:
         # ==============================================================================================================
         # 1. sample latent variables from their variational distributions.
         # ==============================================================================================================
-        if self.deterministic_variational:
-            num_seeds = 1
-            # Use the means of variational distributions as the sole deterministic MC sample.
-            # NOTE: here we don't need to sample the obs2prior weight H since we only compute the log-likelihood.
-            # TODO: is this correct?
-            sample_dict = dict()
-            for coef_name, coef in self.coef_dict.items():
-                sample_dict[coef_name] = coef.variational_distribution.mean.unsqueeze(
-                    dim=0)  # (1, num_*, dim)
-        else:
-            sample_dict = self.sample_coefficient_dictionary(num_seeds)
+        sample_dict = self.sample_coefficient_dictionary(num_seeds, self.deterministic_variational)
 
         # ==============================================================================================================
         # 2. compute log p(latent) prior.
@@ -1341,21 +1405,18 @@ def elbo(self, batch: ChoiceDataset, num_seeds: int = 1) -> torch.Tensor:
         # ==============================================================================================================
         if self.pred_item:
             # the prediction target is item_index.
-            elbo_expanded = self.forward(batch,
+            elbo += self.forward(batch,
                                  return_type='log_prob',
                                  return_scope='item_index',
-                                 deterministic=self.deterministic_variational,
-                                 sample_dict=sample_dict)
-            if self.deterministic_variational:
-                elbo_expanded = elbo_expanded.unsqueeze(dim=0)
-            elbo += elbo_expanded.sum(dim=1).mean(dim=0)  # (num_seeds, len(batch)) --> scalar.
+                                 deterministic=False,
+                                 sample_dict=sample_dict).sum(dim=1).mean(dim=0)
         else:
             # the prediction target is binary.
             # TODO: update the prediction function.
             utility = self.forward(batch,
                                    return_type='utility',
                                    return_scope='item_index',
-                                   deterministic=self.deterministic_variational,
+                                   deterministic=False,
                                    sample_dict=sample_dict)  # (num_seeds, len(batch))
 
             # compute the log-likelihood for binary label.
diff --git a/bemb/model/bemb_flex_lightning.py b/bemb/model/bemb_flex_lightning.py
index 7779cb4..0c7dbee 100644
--- a/bemb/model/bemb_flex_lightning.py
+++ b/bemb/model/bemb_flex_lightning.py
@@ -25,13 +25,18 @@
 
 class LitBEMBFlex(pl.LightningModule):
 
-    def __init__(self, learning_rate: float = 0.3, num_seeds: int = 1, **kwargs):
+    def __init__(self,
+                 learning_rate: float = 0.3,
+                 num_seeds: int = 1,
+                 model_optimizer: str = "Adam",
+                 **kwargs):
         """The initialization method of the wrapper model.
 
         Args:
             learning_rate (float, optional): the learning rate of optimization. Defaults to 0.3.
             num_seeds (int, optional): number of random seeds for the Monte Carlo estimation in the variational inference.
                 Defaults to 1.
+            model_optimizer (str, optional): the optimizer used for training the model. Defaults to "Adam".
             **kwargs: all keyword arguments used for constructing the wrapped BEMB model.
         """
         # use kwargs to pass parameter to BEMB Torch.
@@ -39,9 +44,21 @@ def __init__(self, learning_rate: float = 0.3, num_seeds: int = 1, **kwargs):
         self.model = BEMBFlex(**kwargs)
         self.num_seeds = num_seeds
         self.learning_rate = learning_rate
+        self.optimizer_class_string = model_optimizer
 
     def __str__(self) -> str:
-        return str(self.model)
+        return str(self.model) + '\nOptimizer: ' + str(self.optimizer_class_string) + ', Learning rate: ' + str(self.learning_rate)
+
+    def __repr__(self) -> str:
+        return str(self)
+
+    def state_dict(self) -> dict:
+        # syntax sugar for easily assessing state dict of the model.
+        return self.model.state_dict()
+
+    def load_state_dict(self, state_dict: dict) -> None:
+        # syntax sugar for easily loading state dict of the model.
+        self.model.load_state_dict(state_dict)
 
     def forward(self, *args, **kwargs):
         """Calls the forward method of the wrapped BEMB model, please refer to the documentation of the BEMB class
@@ -62,11 +79,24 @@ def training_step(self, batch, batch_idx):
         loss = - elbo
         return loss
 
+    # DEBUG_MARKER
+    '''
+    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
+        print(f"Epoch {self.current_epoch} has ended")
+        breakpoint()
+    '''
+    # DEBUG_MARKER
+
     def _get_performance_dict(self, batch):
         if self.model.pred_item:
             log_p = self.model(batch, return_type='log_prob',
                                return_scope='all_items', deterministic=True).cpu().numpy()
             num_classes = log_p.shape[1]
+            # y_pred = self.model(batch, return_type='utility', return_scope='all_items', deterministic=True).cpu().numpy().argmax(axis=1)
+            # y = self.model(batch, return_type='log_prob', return_scope='all_items', deterministic=True)
+
+
+
             y_pred = np.argmax(log_p, axis=1)
             y_true = batch.item_index.cpu().numpy()
             performance = {'acc': metrics.accuracy_score(y_true=y_true, y_pred=y_pred),
@@ -119,10 +149,9 @@ def test_step(self, batch, batch_idx):
             self.log('test_' + key, val, prog_bar=True, batch_size=len(batch))
 
     def configure_optimizers(self):
-        optimizer = torch.optim.Adam(self.parameters(), lr=self.learning_rate)
-        return optimizer
+        return getattr(torch.optim, self.optimizer_class_string)(self.parameters(), lr=self.learning_rate)
 
-    def fit_model(self, dataset_list: List[ChoiceDataset], batch_size: int=-1, num_epochs: int=10, num_workers: int=8, **kwargs) -> "LitBEMBFlex":
+    def fit_model(self, dataset_list: List[ChoiceDataset], batch_size: int=-1, num_epochs: int=10, num_workers: int=8, device: str="cpu", **kwargs) -> "LitBEMBFlex":
         """A standard pipeline of model training and evaluation.
 
         Args:
@@ -156,7 +185,10 @@ def section_print(input_text):
         test = create_data_loader(dataset_list[2], batch_size=batch_size // 10, shuffle=False, num_workers=num_workers)
 
         section_print('train the model')
-        trainer = pl.Trainer(gpus=1 if ('cuda' in str(self)) else 0,  # use GPU if the model is currently on the GPU.
+        # TODO: need to change this.
+        trainer = pl.Trainer(# gpus=1 if ('cuda' in str(self)) else 0,  # use GPU if the model is currently on the GPU.
+                            accelerator="cuda" if "cuda" in device else device,  # note: "cuda:0" is not a accelerator name.
+                            devices="auto",
                             max_epochs=num_epochs,
                             check_val_every_n_epoch=1,
                             log_every_n_steps=1,
diff --git a/bemb/utils/run_helper.py b/bemb/utils/run_helper.py
index 410745d..0d5637a 100644
--- a/bemb/utils/run_helper.py
+++ b/bemb/utils/run_helper.py
@@ -17,7 +17,7 @@ def section_print(input_text):
     print('=' * 20, input_text, '=' * 20)
 
 
-def run(model: LitBEMBFlex, dataset_list: List[ChoiceDataset], batch_size: int=-1, num_epochs: int=10, num_workers: int=8, **kwargs) -> LitBEMBFlex:
+def run(model: LitBEMBFlex, dataset_list: List[ChoiceDataset], batch_size: int=-1, num_epochs: int=10, num_workers: int=8, run_test=True, **kwargs) -> LitBEMBFlex:
     """A standard pipeline of model training and evaluation.
 
     Args:
@@ -25,6 +25,7 @@ def run(model: LitBEMBFlex, dataset_list: List[ChoiceDataset], batch_size: int=-
         dataset_list (List[ChoiceDataset]): train_dataset, validation_test, and test_dataset in a list of length 3.
         batch_size (int, optional): batch_size for training and evaluation. Defaults to -1, which indicates full-batch training.
         num_epochs (int, optional): number of epochs for training. Defaults to 10.
+        run_test (bool, optional): whether to run evaluation on test set. Defaults to True.
         **kwargs: additional keyword argument for the pytorch-lightning Trainer.
 
     Returns:
@@ -57,6 +58,7 @@ def run(model: LitBEMBFlex, dataset_list: List[ChoiceDataset], batch_size: int=-
     trainer.fit(model, train_dataloaders=train, val_dataloaders=validation)
     print(f'time taken: {time.time() - start_time}')
 
-    section_print('test performance')
-    trainer.test(model, dataloaders=test)
+    if run_test:
+        section_print('test performance')
+        trainer.test(model, dataloaders=test)
     return model
diff --git a/bemb/utils/run_helper_lightning.py b/bemb/utils/run_helper_lightning.py
new file mode 100644
index 0000000..bc4e402
--- /dev/null
+++ b/bemb/utils/run_helper_lightning.py
@@ -0,0 +1,107 @@
+"""
+This is a template script for researchers to train the PyTorch-based model with minimal effort.
+The researcher only needs to initialize the dataset and the model, this training template comes with default
+hyper-parameters including batch size and learning rate. The researcher should experiment with different levels
+of hyper-parameter if the default setting doesn't converge well.
+"""
+import time
+from typing import Optional
+
+import pytorch_lightning as pl
+from torch_choice.data import ChoiceDataset
+from torch_choice.data.utils import create_data_loader
+
+from bemb.model import LitBEMBFlex
+
+
+def section_print(input_text):
+    """Helper function for printing"""
+    print('=' * 20, input_text, '=' * 20)
+
+
+def run(model: "LitBEMBFlex",
+        dataset_train: ChoiceDataset,
+        dataset_val: Optional[ChoiceDataset]=None,
+        dataset_test: Optional[ChoiceDataset]=None,
+        batch_size: int=-1,
+        num_epochs: int=10,
+        num_workers: int=0,
+        device: Optional[str]=None,
+        check_val_every_n_epoch: Optional[int]=None,
+        **kwargs) -> "LitBEMBFlex":
+    """_summary_
+
+    Args:
+        model (LitBEMBFlex): the initialized BEMB model.
+        dataset_train (ChoiceDataset): the dataset for training.
+        dataset_val (ChoiceDataset): an optional dataset for validation.
+        dataset_test (ChoiceDataset): an optional dataset for testing.
+        batch_size (int, optional): batch size for model training. Defaults to -1.
+        num_epochs (int, optional): number of epochs for the training. Defaults to 10.
+        num_workers (int, optional): number of parallel workers for data loading. Defaults to 0.
+        device (Optional[str], optional): the device that trains the model, if None is specified, the function will
+            use the current device of the provided model. Defaults to None.
+        check_val_every_n_epoch (Optional[int], optional): the frequency of validation, if None is specified,
+            validation will be performed every 10% of total epochs. Defaults to None.
+        **kwargs: other keyword arguments for the pytorch lightning trainer, this is for users with experience in
+            pytorch lightning and wish to customize the training process.
+
+    Returns:
+        LitBEMBFlex: the trained model with estimated parameters in it.
+    """
+    # ==================================================================================================================
+    # Setup the lightning wrapper.
+    # ==================================================================================================================
+    lightning_model = model
+    if device is None:
+        # infer from the model device.
+        device = str(model.device)
+    # the cloned model will be used for standard error calculation later.
+    # model_clone = deepcopy(model)
+    section_print('model received')
+    print(model)
+
+    # ==================================================================================================================
+    # Prepare the data.
+    # ==================================================================================================================
+    # present a summary of datasets received.
+    section_print('data set received')
+    print('[Train dataset]', dataset_train)
+    print('[Validation dataset]', dataset_val)
+    print('[Test dataset]', dataset_test)
+
+    # create pytorch dataloader objects.
+    train_dataloader = create_data_loader(dataset_train.to(device), batch_size=batch_size, shuffle=True, num_workers=num_workers)
+
+    if dataset_val is not None:
+        val_dataloader = create_data_loader(dataset_val.to(device), batch_size=batch_size, shuffle=False, num_workers=num_workers)
+    else:
+        val_dataloader = None
+
+    if dataset_test is not None:
+        test_dataloader = create_data_loader(dataset_test.to(device), batch_size=batch_size, shuffle=False, num_workers=num_workers)
+    else:
+        test_dataloader = None
+
+    # ==================================================================================================================
+    # Training the model.
+    # ==================================================================================================================
+    # training BEMB is more complicated, don't add early stopping for now.
+    callbacks = []
+
+    trainer = pl.Trainer(accelerator="cuda" if "cuda" in device else device,  # note: "cuda:0" is not a accelerator name.
+                         devices="auto",
+                         max_epochs=num_epochs,
+                         check_val_every_n_epoch=num_epochs // 10 if check_val_every_n_epoch is None else check_val_every_n_epoch,
+                         log_every_n_steps=1,
+                         callbacks=callbacks,
+                         **kwargs)
+    start_time = time.time()
+    trainer.fit(lightning_model, train_dataloaders=train_dataloader, val_dataloaders=val_dataloader)
+    print(f'Time taken for training: {time.time() - start_time}')
+    if test_dataloader is not None:
+        trainer.test(lightning_model, test_dataloader)
+    else:
+        print('Skip testing, no test dataset is provided.')
+
+    return model
diff --git a/setup.py b/setup.py
index c76e180..9c1ab40 100644
--- a/setup.py
+++ b/setup.py
@@ -11,7 +11,7 @@
 # This call to setup() does all the work
 setup(
     name="bemb",
-    version="0.1.5",
+    version="0.1.7",
     description="A Pytorch Backend Library for Choice Modelling with Bayesian Matrix Factorization",
     long_description=README,
     long_description_content_type="text/markdown",
diff --git a/tests/simulate_choice_dataset.py b/tests/simulate_choice_dataset.py
index decf57b..cebe980 100644
--- a/tests/simulate_choice_dataset.py
+++ b/tests/simulate_choice_dataset.py
@@ -40,3 +40,59 @@ def simulate_dataset(num_users: int, num_items: int, data_size: int) -> List[Cho
 
     dataset_list = [dataset[train_idx], dataset[val_idx], dataset[test_idx]]
     return dataset_list
+
+
+def simulate_dataset_v2(num_users: int, num_items: int, num_sessions: int, data_size: int) -> List[ChoiceDataset]:
+    length_of_dataset = data_size  # $N$
+    # create observables/features, the number of parameters are arbitrarily chosen.
+    # generate 128 features for each user, e.g., race, gender.
+    # these variables should have shape (num_users, *)
+    user_obs = torch.randn(num_users, 128)
+    # generate 64 features for each user, e.g., quality.
+    item_obs = torch.randn(num_items, 64)
+    # generate 10 features for each session, e.g., weekday indicator.
+    session_obs = torch.randn(num_sessions, 10)
+    # generate 12 features for each session user pair, e.g., the budget of that user at the shopping day.
+    itemsession_obs = torch.randn(num_sessions, num_items, 12)
+    # generate 12 features for each user item pair, e.g., the user's preference on that item.
+    useritem_obs = torch.randn(num_users, num_items, 12)
+    # generate 10 user-session specific observables, e.g., the historical spending amount of that user at that session.
+    usersession_obs = torch.randn(num_users, num_sessions, 10)
+    # generate 8 features for each user session item triple, e.g., the user's preference on that item at that session.
+    # since `U*S*I` is potentially huge and may cause identifiability issues, we rarely use this kind of observable in practice.
+    usersessionitem_obs = torch.randn(num_users, num_sessions, num_items, 8)
+
+    # generate the array of item[n].
+    item_index = torch.LongTensor(np.random.choice(num_items, size=length_of_dataset))
+    # generate the array of user[n].
+    user_index = torch.LongTensor(np.random.choice(num_users, size=length_of_dataset))
+    # generate the array of session[n].
+    session_index = torch.LongTensor(np.random.choice(num_sessions, size=length_of_dataset))
+
+    # assume all items are available in all sessions.
+    item_availability = torch.ones(num_sessions, num_items).bool()
+
+    dataset = ChoiceDataset(
+        # pre-specified keywords of __init__
+        item_index=item_index,  # required.
+        num_items=num_items,
+        # optional:
+        user_index=user_index,
+        num_users=num_users,
+        session_index=session_index,
+        item_availability=item_availability,
+        # additional keywords of __init__
+        user_obs=user_obs,
+        item_obs=item_obs,
+        session_obs=session_obs,
+        itemsession_obs=itemsession_obs,
+        useritem_obs=useritem_obs,
+        usersession_obs=usersession_obs,
+        usersessionitem_obs=usersessionitem_obs)
+
+    # we can subset the dataset by conventional python indexing.
+    dataset_train = dataset[:int(0.8*len(dataset))]
+    dataset_val = dataset[int(0.8*len(dataset)):int(0.9*len(dataset))]
+    dataset_test = dataset[int(0.9*len(dataset)):]
+
+    return [dataset_train, dataset_val, dataset_test]
diff --git a/tests/test_bemb_functionality.py b/tests/test_bemb_functionality.py
index cf96aa5..1037267 100644
--- a/tests/test_bemb_functionality.py
+++ b/tests/test_bemb_functionality.py
@@ -17,6 +17,7 @@
 global numUs, num_items, data_size
 num_users = 50
 num_items = 100
+num_sessions = 500
 data_size = 10000
 num_seeds = 32
 
@@ -35,20 +36,6 @@ def test_parser_and_model_creation(self):
         self.assertTrue(additive_decomposition[5]['coefficient'] == ['delta_item'] and additive_decomposition[5]['observable'] == 'item_obs')
         self.assertTrue(additive_decomposition[6]['coefficient'] == ['comp_user', 'comp_item'] and additive_decomposition[6]['observable'] == 'user_obs')
 
-    def test_parser_price_and_itemsession_obs_1(self):
-        formula_1 = 'alpha_item * price_obs'
-        formula_2 = 'alpha_item * itemsession_obs'
-        u1 = parse_utility(formula_1)
-        u2 = parse_utility(formula_2)
-        self.assertTrue(u1 == u2)
-
-    def test_parser_price_and_itemsession_obs_2(self):
-        formula_1 = 'alpha_item * price_obs + user_obs * gamma_user + item_obs * delta_item'
-        formula_2 = 'alpha_item * itemsession_obs + user_obs * gamma_user + item_obs * delta_item'
-        u1 = parse_utility(formula_1)
-        u2 = parse_utility(formula_2)
-        self.assertTrue(u1 == u2)
-
     def test_parser_constant_and_null_coef(self):
         formula_1 = 'user_obs * gamma_constant + alpha_item * beta_item'
         formula_2 = 'user_obs * gamma + alpha_item * beta_item'
@@ -56,14 +43,6 @@ def test_parser_constant_and_null_coef(self):
         u2 = parse_utility(formula_2)
         self.assertTrue(u1 == u2)
 
-    def test_parser(self):
-        formula_1 = 'price_obs * gamma_constant + alpha_item * beta_item'
-        formula_2 = 'itemsession_obs * gamma + alpha_item * beta_item'
-
-        u1 = parse_utility(formula_1)
-        u2 = parse_utility(formula_2)
-        self.assertTrue(u1 == u2)
-
 class TestBEMBFlex(unittest.TestCase):
     """
     Testing core functionality of bemb.
@@ -134,20 +113,76 @@ def test_predict_proba_shape(self):
         dataset_list = simulate_choice_dataset.simulate_dataset(num_users=num_users, num_items=num_items, data_size=data_size)
         batch = dataset_list[-1]
 
-        for pred_item in [True, False]:
+
+class TestBEMBFlexV2(unittest.TestCase):
+    """
+    Testing core functionality of bemb.
+    """
+    # def __init__(self):
+    #     pass
+
+    # def test_initialization(self):
+    #    pass
+
+    # def test_estimation(self):
+    #     pass
+
+    # ==================================================================================================================
+    # Test Arguments and Options in the Initialization Method
+    # ==================================================================================================================
+    def test_init(self):
+        pass
+
+    def test_H_zero_mask(self):
+        pass
+
+    # ==================================================================================================================
+    # Test API Methods
+    # ==================================================================================================================
+    def test_prediction_shapes(self):
+        dataset_list = simulate_choice_dataset.simulate_dataset_v2(num_users=num_users, num_items=num_items, num_sessions=num_sessions, data_size=data_size)
+        batch = dataset_list[0]
+        # test different variations of the forward function.
+        # return_type X return_scope X deterministic X pred_items.
+        for return_type, return_scope, deterministic, pred_item in itertools.product(['utility', 'log_prob'], ['item_index', 'all_items'], [True, False], [True, False]):
+            if not pred_item:
+                # generate fake binary labels.
+                batch.label = torch.LongTensor(np.random.randint(2, size=len(batch)))
+
+            # initialize the model.
             bemb = BEMBFlex(
                 pred_item=pred_item,
-                utility_formula='theta_user * alpha_item',
+                utility_formula="a_user + b_item + c_constant + d_user * e_item + f1_constant * user_obs + f2_constant * item_obs + f3_constant * session_obs + f4_constant * useritem_obs + f5_constant * usersession_obs + f6_constant * itemsession_obs + f7_constant * usersessionitem_obs",
                 num_users=num_users,
                 num_items=num_items,
+                num_sessions=num_sessions,
                 num_classes=None if pred_item else 2,
-                num_user_obs=dataset_list[0].user_obs.shape[1],
-                num_item_obs=dataset_list[0].item_obs.shape[1],
-                obs2prior_dict={'theta_user': True, 'alpha_item': True},
-                coef_dim_dict={'theta_user': 10, 'alpha_item': 10}
+                num_user_obs=batch.user_obs.shape[1],
+                num_item_obs=batch.item_obs.shape[1],
+                obs2prior_dict={'a_user': True, 'b_item': True, 'c_constant': False, 'd_user': True, 'e_item': True,
+                                'f1_constant': False, 'f2_constant': False, 'f3_constant': False, 'f4_constant': False, 'f5_constant': False, 'f6_constant': False, 'f7_constant': False},
+                coef_dim_dict={'a_user': 1, 'b_item': 1, 'c_constant': 1, 'd_user': 10, 'e_item': 10,
+                                'f1_constant': batch.user_obs.shape[-1], 'f2_constant': batch.item_obs.shape[-1], 'f3_constant': batch.session_obs.shape[-1],
+                                'f4_constant': batch.useritem_obs.shape[-1] , 'f5_constant': batch.usersession_obs.shape[-1], 'f6_constant': batch.itemsession_obs.shape[-1], 'f7_constant': batch.usersessionitem_obs.shape[-1]}
             )
-            P = bemb.predict_proba(batch)
 
+            output = bemb.forward(batch,
+                                  return_type=return_type, return_scope=return_scope,
+                                  deterministic=deterministic,
+                                  sample_dict=None,
+                                  num_seeds=num_seeds)
+
+            if (return_scope == 'item_index') and (deterministic == True):
+                self.assertEqual(output.shape, (len(batch),))
+            elif (return_scope == 'all_items') and (deterministic == True):
+                self.assertEqual(output.shape, (len(batch), num_items))
+            elif (return_scope == 'item_index') and (deterministic == False):
+                self.assertEqual(output.shape, (num_seeds, len(batch)))
+            elif (return_scope == 'item_index') and (deterministic == False):
+                self.assertEqual(output.shape, (num_seeds, len(batch), num_items))
+
+            # test predict_proba method.
+            P = bemb.predict_proba(batch)
             if pred_item:
                 self.assertEqual(P.shape, (len(batch), num_items))
             else:
diff --git a/tutorials/simulation/optimizers.ipynb b/tutorials/simulation/optimizers.ipynb
new file mode 100644
index 0000000..c3e81fc
--- /dev/null
+++ b/tutorials/simulation/optimizers.ipynb
@@ -0,0 +1,478 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tutorial for Using Different Optimizers for `bemb`.\n",
+    "\n",
+    "Author: Tianyu Du\n",
+    "\n",
+    "Update: May. 19, 2023\n",
+    "\n",
+    "This tutorial offers a simple simulation exercise to demonstrate how to use BEMB model and the power of BEMB's `obs2prior` feature. We highly recommend you to read the BEMB tutorial first."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import bemb\n",
+    "from bemb.data import load_simulation_dataset\n",
+    "from bemb.model import LitBEMBFlex\n",
+    "from bemb import run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.13.0+cu117\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(torch.__version__)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "No `session_index` is provided, assume each choice instance is in its own session.\n"
+     ]
+    }
+   ],
+   "source": [
+    "num_users = 1500\n",
+    "num_items = 50\n",
+    "data_size = 1000\n",
+    "dataset_train, dataset_val, dataset_test  = load_simulation_dataset(num_users=num_users, num_items=num_items, data_size=data_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['theta_user', 'alpha_item'], 'observable': None}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "LATENT_DIM = 10  # the dimension of alpha and theta.\n",
+    "bemb = LitBEMBFlex(\n",
+    "    learning_rate=0.01,  # set the learning rate, feel free to play with different levels.\n",
+    "    pred_item=True,  # let the model predict item_index, don't change this one.\n",
+    "    num_seeds=256,  # number of Monte Carlo samples for estimating the ELBO.\n",
+    "    utility_formula='theta_user * alpha_item',  # the utility formula.\n",
+    "    num_users=num_users,\n",
+    "    num_items=num_items,\n",
+    "    num_user_obs=dataset_train.user_obs.shape[1],\n",
+    "    num_item_obs=dataset_train.item_obs.shape[1],\n",
+    "    # whether to turn on obs2prior for each parameter.\n",
+    "    obs2prior_dict={'theta_user': True, 'alpha_item': True},\n",
+    "    # the dimension of latents, since the utility is an inner product of theta and alpha, they should have\n",
+    "    # the same dimension.\n",
+    "    coef_dim_dict={'theta_user': LATENT_DIM, 'alpha_item': LATENT_DIM},\n",
+    "    model_optimizer=\"Adam\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Bayesian EMBedding Model with U[user, item, session] = theta_user * alpha_item\n",
+       "Total number of parameters: 33000.\n",
+       "With the following coefficients:\n",
+       "ModuleDict(\n",
+       "  (theta_user): BayesianCoefficient(num_classes=1500, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 50]), X_obs shape=50), Ix1.0))\n",
+       "  (alpha_item): BayesianCoefficient(num_classes=50, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 50]), X_obs shape=50), Ix1.0))\n",
+       ")\n",
+       "[]\n",
+       "Optimizer: Adam, Learning rate: 0.01"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bemb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = theta_user * alpha_item\n",
+      "Total number of parameters: 33000.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (theta_user): BayesianCoefficient(num_classes=1500, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 50]), X_obs shape=50), Ix1.0))\n",
+      "  (alpha_item): BayesianCoefficient(num_classes=50, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 50]), X_obs shape=50), Ix1.0))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.01\n",
+      "==================== data set received ====================\n",
+      "[Train dataset] ChoiceDataset(label=[], item_index=[800], user_index=[800], session_index=[800], item_availability=[], user_obs=[1500, 50], item_obs=[50, 50], device=cpu)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[100], user_index=[100], session_index=[100], item_availability=[], user_obs=[1500, 50], item_obs=[50, 50], device=cpu)\n",
+      "[Test dataset] ChoiceDataset(label=[], item_index=[100], user_index=[100], session_index=[100], item_availability=[], user_obs=[1500, 50], item_obs=[50, 50], device=cpu)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 33.0 K\n",
+      "-----------------------------------\n",
+      "33.0 K    Trainable params\n",
+      "0         Non-trainable params\n",
+      "33.0 K    Total params\n",
+      "0.132     Total estimated model params size (MB)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e9c6259fae5844528c1a8444f6b5057c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Sanity Checking: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2c9478be8bd946b3a529618952afc5a6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Training: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "722bb70da2aa49718105ba399ec5691b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5760fd4f359d4c9daf49e19c1daeda11",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4cd77185a9fc48cfbb94fbe31e634bb4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d819969801e64e11be31ae35585552a0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "da5d475532534feea636bcae46520447",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1b127ca4d7744d2d9c275f632b1f5046",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "26ecc477c8554db48deb7d130abb0865",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3c4dc13bec224a08841157d437b31d80",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c14aa2049b26425a8a81a8933cfde0fc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "dc6aefee52664f06a54367c12b62e85a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Validation: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "`Trainer.fit` stopped: `max_epochs=1000` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Time taken for training: 193.26278162002563\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a6256eaf618a412eaeb2772345b68b60",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Testing: 0it [00:00, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.37            </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -9.440007950868457     </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.37           \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -9.440007950868457    \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Bayesian EMBedding Model with U[user, item, session] = theta_user * alpha_item\n",
+       "Total number of parameters: 33000.\n",
+       "With the following coefficients:\n",
+       "ModuleDict(\n",
+       "  (theta_user): BayesianCoefficient(num_classes=1500, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 50]), X_obs shape=50), Ix1.0))\n",
+       "  (alpha_item): BayesianCoefficient(num_classes=50, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 50]), X_obs shape=50), Ix1.0))\n",
+       ")\n",
+       "[]\n",
+       "Optimizer: Adam, Learning rate: 0.01"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "run(bemb, dataset_train=dataset_train, dataset_val=dataset_val, dataset_test=dataset_test,\n",
+    "    batch_size=len(dataset_train) // 20, num_epochs=1000, device=\"cuda\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.7 ('ml')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": true
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "5859d33511df864b0b7226a715510a0165ef032ed4b83eb4ae2c092f0788759c"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/tutorials/simulation/paper_demo.ipynb b/tutorials/simulation/paper_demo.ipynb
new file mode 100644
index 0000000..e588b59
--- /dev/null
+++ b/tutorials/simulation/paper_demo.ipynb
@@ -0,0 +1,418 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BEMB Paper Code Demonstration\n",
+    "This file contains code demonstrated in our BEMB paper, readers can run the code in this file to reproduce the results in our paper or modify the code to fit their own needs.\n",
+    "\n",
+    "Readers can refer to the `torch-choice` paper or `torch-choice` documentation website for more details about the `ChoiceDataset` data structure.\n",
+    "\n",
+    "Code for simulation studies is in another separate notebook.\n",
+    "\n",
+    "> Author: Tianyu Du\n",
+    ">\n",
+    "> Date: Sept. 12, 2023"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import numpy as np\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch_choice\n",
+    "from torch_choice.data import ChoiceDataset\n",
+    "\n",
+    "import bemb\n",
+    "from bemb.model import LitBEMBFlex\n",
+    "from bemb.utils.run_helper import run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.__version__=2.0.1\n",
+      "torch.cuda.is_available()=False\n",
+      "torch_choice.__version__=1.0.4a\n",
+      "bemb.__version__=0.1.6\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"{torch.__version__=:}\")\n",
+    "print(f\"{torch.cuda.is_available()=:}\")\n",
+    "print(f\"{torch_choice.__version__=:}\")\n",
+    "print(f\"{bemb.__version__=:}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<torch._C.Generator at 0x115985190>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# for reproducibility, fix random seeds.\n",
+    "random.seed(1234)\n",
+    "np.random.seed(1234)\n",
+    "torch.random.manual_seed(1234)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if torch.cuda.is_available():\n",
+    "    DEVICE = \"cuda\"\n",
+    "else:\n",
+    "    DEVICE = \"cpu\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Generate Random Information for Demonstration\n",
+    "Here we will use randomly generated information to illustrate the usage of `ChoiceDataset`. Observable tensors are classified by how they vary by user, item, and session. The package is expecting particular shapes of these observable tensors based on their types."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Feel free to modify it as you want.\n",
+    "num_users = 10  # $U$\n",
+    "num_items = 4  # $I$\n",
+    "num_sessions = 500  # $S$\n",
+    "\n",
+    "length_of_dataset = 10000  # $N$\n",
+    "# create observables/features, the number of parameters are arbitrarily chosen.\n",
+    "# generate 128 features for each user, e.g., race, gender.\n",
+    "# these variables should have shape (num_users, *)\n",
+    "user_obs = torch.randn(num_users, 128)\n",
+    "# generate 64 features for each user, e.g., quality.\n",
+    "item_obs = torch.randn(num_items, 64)\n",
+    "# generate 10 features for each session, e.g., weekday indicator. \n",
+    "session_obs = torch.randn(num_sessions, 10)\n",
+    "# generate 12 features for each session user pair, e.g., the budget of that user at the shopping day.\n",
+    "itemsession_obs = torch.randn(num_sessions, num_items, 12)\n",
+    "# generate 12 features for each user item pair, e.g., the user's preference on that item.\n",
+    "useritem_obs = torch.randn(num_users, num_items, 12)\n",
+    "# generate 10 user-session specific observables, e.g., the historical spending amount of that user at that session.\n",
+    "usersession_obs = torch.randn(num_users, num_sessions, 10)\n",
+    "# generate 8 features for each user session item triple, e.g., the user's preference on that item at that session.\n",
+    "# since `U*S*I` is potentially huge and may cause identifiability issues, we rarely use this kind of observable in practice.\n",
+    "usersessionitem_obs = torch.randn(num_users, num_sessions, num_items, 8)\n",
+    "\n",
+    "# generate the array of item[n].\n",
+    "item_index = torch.LongTensor(np.random.choice(num_items, size=length_of_dataset))\n",
+    "# generate the array of user[n].\n",
+    "user_index = torch.LongTensor(np.random.choice(num_users, size=length_of_dataset))\n",
+    "# generate the array of session[n].\n",
+    "session_index = torch.LongTensor(np.random.choice(num_sessions, size=length_of_dataset))\n",
+    "\n",
+    "# assume all items are available in all sessions.\n",
+    "item_availability = torch.ones(num_sessions, num_items).bool()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = ChoiceDataset(\n",
+    "    # pre-specified keywords of __init__\n",
+    "    item_index=item_index,  # required.\n",
+    "    num_items=num_items,\n",
+    "    # optional:\n",
+    "    user_index=user_index,\n",
+    "    num_users=num_users,\n",
+    "    session_index=session_index,\n",
+    "    item_availability=item_availability,\n",
+    "    # additional keywords of __init__\n",
+    "    user_obs=user_obs,\n",
+    "    item_obs=item_obs,\n",
+    "    session_obs=session_obs,\n",
+    "    itemsession_obs=itemsession_obs,\n",
+    "    useritem_obs=useritem_obs,\n",
+    "    usersession_obs=usersession_obs,\n",
+    "    usersessionitem_obs=usersessionitem_obs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "user_obs: torch.Size([10000, 4, 128])\n",
+      "item_obs: torch.Size([10000, 4, 64])\n",
+      "session_obs: torch.Size([10000, 4, 10])\n",
+      "itemsession_obs: torch.Size([10000, 4, 12])\n",
+      "useritem_obs: torch.Size([10000, 4, 12])\n",
+      "usersession_obs: torch.Size([10000, 4, 10])\n",
+      "usersessionitem_obs: torch.Size([10000, 4, 8])\n"
+     ]
+    }
+   ],
+   "source": [
+    "def print_dict(d):\n",
+    "    for k, v in d.items():\n",
+    "        if torch.is_tensor(v):\n",
+    "            print(f\"{k}: {v.shape}\")\n",
+    "print_dict(dataset.x_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# we can subset the dataset by conventional python indexing.\n",
+    "dataset_train = dataset[:8000].to(DEVICE)\n",
+    "dataset_val = dataset[8000:9000].to(DEVICE)\n",
+    "dataset_test = dataset[9000:].to(DEVICE)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Conduct the ELBO Optimization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (mps), used: False\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 34.3 K\n",
+      "-----------------------------------\n",
+      "34.3 K    Trainable params\n",
+      "0         Non-trainable params\n",
+      "34.3 K    Total params\n",
+      "0.137     Total estimated model params size (MB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['alpha_item'], 'observable': None},\n",
+      " {'coefficient': ['beta_user', 'gamma_item'], 'observable': None},\n",
+      " {'coefficient': ['delta_user'], 'observable': 'item_obs'},\n",
+      " {'coefficient': ['eta_item', 'pi_user'], 'observable': 'session_obs'}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = alpha_item + beta_user * gamma_item + delta_user * item_obs + eta_item * pi_user * session_obs\n",
+      "Total number of parameters: 34280.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (alpha_item): BayesianCoefficient(num_classes=4, dimension=1, prior=N(H*X_obs(H shape=torch.Size([1, 64]), X_obs shape=64), Ix1.0))\n",
+      "  (beta_user): BayesianCoefficient(num_classes=10, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 128]), X_obs shape=128), Ix1.0))\n",
+      "  (gamma_item): BayesianCoefficient(num_classes=4, dimension=10, prior=N(H*X_obs(H shape=torch.Size([10, 64]), X_obs shape=64), Ix1.0))\n",
+      "  (delta_user): BayesianCoefficient(num_classes=10, dimension=64, prior=N(H*X_obs(H shape=torch.Size([64, 128]), X_obs shape=128), Ix1.0))\n",
+      "  (eta_item): BayesianCoefficient(num_classes=4, dimension=30, prior=N(H*X_obs(H shape=torch.Size([30, 64]), X_obs shape=64), Ix1.0))\n",
+      "  (pi_user): BayesianCoefficient(num_classes=10, dimension=30, prior=N(H*X_obs(H shape=torch.Size([30, 128]), X_obs shape=128), Ix1.0))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.1\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[500, 4], user_obs=[10, 128], item_obs=[4, 64], session_obs=[500, 10], itemsession_obs=[500, 4, 12], useritem_obs=[10, 4, 12], usersession_obs=[10, 500, 10], usersessionitem_obs=[10, 500, 4, 8], device=cpu)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[500, 4], user_obs=[10, 128], item_obs=[4, 64], session_obs=[500, 10], itemsession_obs=[500, 4, 12], useritem_obs=[10, 4, 12], usersession_obs=[10, 500, 10], usersessionitem_obs=[10, 500, 4, 8], device=cpu)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[500, 4], user_obs=[10, 128], item_obs=[4, 64], session_obs=[500, 10], itemsession_obs=[500, 4, 12], useritem_obs=[10, 4, 12], usersession_obs=[10, 500, 10], usersessionitem_obs=[10, 500, 4, 8], device=cpu)\n",
+      "==================== train the model ====================\n",
+      "Epoch 2: 100%|██████████| 71/71 [00:02<00:00, 33.29it/s, loss=3.44e+03, v_num=45, val_acc=0.248, val_ll=-1.99]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "`Trainer.fit` stopped: `max_epochs=3` reached.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 2: 100%|██████████| 71/71 [00:02<00:00, 33.17it/s, loss=3.44e+03, v_num=45, val_acc=0.248, val_ll=-1.99]\n",
+      "time taken: 6.626070022583008\n",
+      "==================== test performance ====================\n",
+      "Testing DataLoader 0: 100%|██████████| 84/84 [00:00<00:00, 182.67it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.249           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -1.9957098799463049    </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.249          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -1.9957098799463049   \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "bemb = LitBEMBFlex(\n",
+    "    learning_rate=0.1,  # set the learning rate, feel free to play with different levels.\n",
+    "    pred_item=True,  # let the model predict item_index, don't change this one.\n",
+    "    num_seeds=32,  # number of Monte Carlo samples for estimating the ELBO.\n",
+    "    utility_formula=\"alpha_item + beta_user * gamma_item + delta_user * item_obs + eta_item * pi_user * session_obs\",  # the utility formula.\n",
+    "    num_users=num_users,\n",
+    "    num_items=num_items,\n",
+    "    num_sessions=num_sessions,\n",
+    "    num_user_obs=dataset.user_obs.shape[1],\n",
+    "    num_item_obs=dataset.item_obs.shape[1],\n",
+    "    # we use obs2prior on all coefficients, simply change them to False if you want to disable the obs2prior for a particular coefficient.\n",
+    "    obs2prior_dict={\"alpha_item\": True, \n",
+    "                    \"beta_user\": True,\n",
+    "                    \"gamma_item\": True,\n",
+    "                    \"delta_user\": True,\n",
+    "                    \"eta_item\": True,\n",
+    "                    \"pi_user\": True},\n",
+    "    # the dimension of latents, since the utility is an inner product of theta and alpha, they should have\n",
+    "    # the same dimension.\n",
+    "    coef_dim_dict={\"alpha_item\": 1,  # fix effect should always have dimension of 1.\n",
+    "                   # the matrix decomposition term beta_user * gamma_item indicates that beta_user and gamma_item should have the same dimension.\n",
+    "                   # we choose the latent dimension to 10 here.\n",
+    "                   \"beta_user\": 10,\n",
+    "                   \"gamma_item\": 10,\n",
+    "                   # delta_user * item_obs term indicates that delta_user and item_obs should have the same dimension.\n",
+    "                   # and we generated 64 item features above.\n",
+    "                   \"delta_user\": 64,\n",
+    "                   # eta_item * pi_user* session_obs suggests that both of eta_item and pi_user should have the same dimension.\n",
+    "                   # the dimension of them should be the dimension of session_obs (which is 10) multiplied by the latent dimension.\n",
+    "                   # we choose the latent dimension to be 3 here.\n",
+    "                   \"eta_item\": 10*3,\n",
+    "                   \"pi_user\": 10*3},\n",
+    ")\n",
+    "\n",
+    "# move the model to the computing device (e.g., GPU if available).\n",
+    "bemb = bemb.to(DEVICE)\n",
+    "\n",
+    "# estimate the model for 3 epochs.\n",
+    "bemb = bemb.fit_model([dataset_train, dataset_val, dataset_test],\n",
+    "                      batch_size=128, num_epochs=3, num_workers=0, device=DEVICE, enable_progress_bar=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The paper demon notebook has run successfully.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"The paper demon notebook has run successfully.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "dev",
+   "language": "python",
+   "name": "dev"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_1_beta_hat.png b/tutorials/simulation/paper_demo_simulation_results/simulation_1_beta_hat.png
new file mode 100644
index 0000000..b060e74
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_1_beta_hat.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_1_income_coefficients.png b/tutorials/simulation/paper_demo_simulation_results/simulation_1_income_coefficients.png
new file mode 100644
index 0000000..caca157
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_1_income_coefficients.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_2_beta_hat_obs2prior=False.png b/tutorials/simulation/paper_demo_simulation_results/simulation_2_beta_hat_obs2prior=False.png
new file mode 100644
index 0000000..b791208
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_2_beta_hat_obs2prior=False.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_2_beta_hat_obs2prior=True.png b/tutorials/simulation/paper_demo_simulation_results/simulation_2_beta_hat_obs2prior=True.png
new file mode 100644
index 0000000..838ad47
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_2_beta_hat_obs2prior=True.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_2_income_coefficients.png b/tutorials/simulation/paper_demo_simulation_results/simulation_2_income_coefficients.png
new file mode 100644
index 0000000..657ddd8
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_2_income_coefficients.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_3_heatmap.png b/tutorials/simulation/paper_demo_simulation_results/simulation_3_heatmap.png
new file mode 100644
index 0000000..94780f8
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_3_heatmap.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_3_interaction_hat_obs2prior=False.png b/tutorials/simulation/paper_demo_simulation_results/simulation_3_interaction_hat_obs2prior=False.png
new file mode 100644
index 0000000..505e58f
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_3_interaction_hat_obs2prior=False.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_3_interaction_hat_obs2prior=True.png b/tutorials/simulation/paper_demo_simulation_results/simulation_3_interaction_hat_obs2prior=True.png
new file mode 100644
index 0000000..cfb70ea
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_3_interaction_hat_obs2prior=True.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_3_user_preferences.png b/tutorials/simulation/paper_demo_simulation_results/simulation_3_user_preferences.png
new file mode 100644
index 0000000..8875b90
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_3_user_preferences.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_4_coefficients.png b/tutorials/simulation/paper_demo_simulation_results/simulation_4_coefficients.png
new file mode 100644
index 0000000..d8184b6
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_4_coefficients.png differ
diff --git a/tutorials/simulation/paper_demo_simulation_results/simulation_4_interaction_hat_obs2prior=True.png b/tutorials/simulation/paper_demo_simulation_results/simulation_4_interaction_hat_obs2prior=True.png
new file mode 100644
index 0000000..a8cabfe
Binary files /dev/null and b/tutorials/simulation/paper_demo_simulation_results/simulation_4_interaction_hat_obs2prior=True.png differ
diff --git a/tutorials/simulation/simulation_study_paper_demo.ipynb b/tutorials/simulation/simulation_study_paper_demo.ipynb
new file mode 100644
index 0000000..7f8f433
--- /dev/null
+++ b/tutorials/simulation/simulation_study_paper_demo.ipynb
@@ -0,0 +1,1724 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BEMB Demo: Simulation Studies.\n",
+    "\n",
+    "> Author: Tianyu Du (tianyudu@stanford.edu)\n",
+    "\n",
+    "This notebook contains replication materials for the simulation studies in the BEMB paper;\n",
+    "\n",
+    "Before running this notebook, you should create a folder called, to save simulation results (e.g., figures). Please modify the `OUTPUT_DIR` variable below to point to the folder you just created."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTPUT_DIR = \"./paper_demo_simulation_results\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import random\n",
+    "from typing import List\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "import torch\n",
+    "from torch_choice.data import ChoiceDataset\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "from bemb.model import LitBEMBFlex"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<torch._C.Generator at 0x7f4e9a6e9390>"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Fix Random Seeds for Reproducibility.\n",
+    "random.seed(1234)\n",
+    "np.random.seed(1234)\n",
+    "torch.random.manual_seed(1234)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using cuda device.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Please note that `mps` (apple silicon gpus) is not fully supported by PyTorch; therefore, you would need to use `cpu` device on Mac. \n",
+    "if torch.cuda.is_available():\n",
+    "    DEVICE = \"cuda\"\n",
+    "else:\n",
+    "    DEVICE = \"cpu\"\n",
+    "print(f\"Using {DEVICE} device.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# control the quality of figures. Use 75 for preview, use 300 for publication.\n",
+    "# using a larger DPI will increase the file size of the figure and the time to render the figure.\n",
+    "DPI = 300 "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# configure the size of simulation.\n",
+    "num_users = 1_500  # 1500 users in the dataset.\n",
+    "num_items = 50  # 50 items to choose from.\n",
+    "num_sessions = 10  # 10 sessions; sessions are used only in simulation 4.\n",
+    "data_size = 10_000  # 10,000 choice records."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# we assign random users and sessions to each choice record.\n",
+    "user_index = torch.LongTensor(np.random.choice(num_users, size=data_size))\n",
+    "session_index = torch.LongTensor(np.random.choice(num_sessions, size=data_size))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# a helper function to plot distributions of entries in a tensor.\n",
+    "def plot_tensor(tensor):\n",
+    "    fig, ax = plt.subplots(1, 1, figsize=(3, 3), dpi=DPI)\n",
+    "    sns.histplot(tensor.view(-1,).numpy(), bins=40, ax=ax)\n",
+    "    fig.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Simulation Study 1: Item-Level \"Random\" Effect on User Attributes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Simulate Dataset\n",
+    "We first specify the number of users and number of items in the dataset.\n",
+    "The `data_size` denotes the number of user-item choice pairs to generate (i.e., number of observations.)\n",
+    "Each user-item choice pair is called a **purchasing record** in our terminology, you can revise the data management tutorial."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x900 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# generate random user income data.\n",
+    "user_income = (torch.randn(num_users) + 5).clamp(min=0)\n",
+    "# plot the histogram of user income.\n",
+    "plot_tensor(user_income)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x900 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# generate item price data.\n",
+    "item_price = torch.rand(num_items) * 50 + 50\n",
+    "# plot distribution of item prices.\n",
+    "plot_tensor(item_price)\n",
+    "# WLOG, assign the first 25 items to be in the same category (category 1), and the rest to be in the other category (category 0).\n",
+    "item_bin_cate = torch.zeros(num_items).long()\n",
+    "item_bin_cate[:25] = 1\n",
+    "\n",
+    "# combine both information into a tensor of shape (num_items, 2).\n",
+    "item_obs = torch.stack([item_price, item_bin_cate], dim=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generate Item-Specific Random Coefficients and Utilities.\n",
+    "In our first simulation case, the utility $\\mu_{uis}$ is a function of user-income with item-specific coefficient.\n",
+    "\n",
+    "$$\n",
+    "\\mu_{uis} = \\beta_i \\times x^\\text{user income}_u\n",
+    "$$\n",
+    "\n",
+    "The item-specific coefficient $\\beta_i$ is generated as a stochastic function of item prices. For high price items, income boost utility (e.g., luxury items). For low price items, low income boost utility. Please refer to the BEMB paper for a more detailed description of the simulation setup."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 2400x1800 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# generate $beta_i$ for simulation study.\n",
+    "scaled_price = (item_price - torch.min(item_price))/ (torch.max(item_price) - torch.min(item_price)) - 0.5\n",
+    "beta_item = torch.randn_like(scaled_price)*torch.std(scaled_price) + scaled_price\n",
+    "\n",
+    "# plot the relationship between $price_i$ and $beta_i$.\n",
+    "fig, ax = plt.subplots(figsize=(8, 6), dpi=DPI)\n",
+    "sns.regplot(x=item_price.squeeze().numpy(), y=beta_item.numpy(), ax=ax)\n",
+    "ax.set_xlabel(\"$price_i$\")\n",
+    "ax.set_ylabel(\"$beta_i$\")\n",
+    "fig.savefig(os.path.join(OUTPUT_DIR, 'simulation_1_income_coefficients.png'), dpi=DPI, bbox_inches='tight')\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# compute the utility $\\mu_{uis}$ for each user $u$, item $i$, and session $s$.\n",
+    "# there is no session effect in this simulation study, hence $\\mu_{uis}$ is the same for all $s$.\n",
+    "utility = torch.zeros(num_users, num_items, num_sessions)\n",
+    "for u in range(num_users):\n",
+    "    for i in range(num_items):\n",
+    "        for s in range(num_sessions):\n",
+    "            utility[u, i, s] = beta_item[i] * user_income[u]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x900 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# distribution of U*I*S utility entries.\n",
+    "plot_tensor(utility)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generate Random Choices based on Utilities."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "item_index = torch.empty(data_size, dtype=torch.long)\n",
+    "for idx in range(data_size):\n",
+    "    # get the user and session index corresponding to each choice record.\n",
+    "    u = user_index[idx]\n",
+    "    s = session_index[idx]\n",
+    "    utility_list = utility[u, :, s]  # list of utility values for all items in the session.\n",
+    "    p = torch.softmax(utility_list, dim=0).numpy()  # soft-max transform utilities to probabilities in multinominal distribution.\n",
+    "    assert abs(np.sum(p) - 1) < 1e-5  # check if the sum of probabilities is 1.\n",
+    "    # randomly choose an item from the multinominal distribution with probabilities p.\n",
+    "    item_index[idx] = np.random.choice(num_items, p=p)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def report_most_least_bought_items(item_index: torch.LongTensor):\n",
+    "    # report most bought and least bought items.\n",
+    "    vc = pd.DataFrame(data={\"item\": item_index.squeeze().numpy()}).value_counts(normalize=True).sort_values(ascending=False)\n",
+    "    print(\"Most bought item with their frequencies:\")\n",
+    "    print(vc.head())\n",
+    "    print(\"Least bought item with their frequencies:\")\n",
+    "    print(vc.tail())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Build Choice Dataset\n",
+    "Please refer to our `torch-choice` paper for more details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def split_dataset_into_train_val_test(D: ChoiceDataset) -> List[ChoiceDataset]:\n",
+    "    # split dataset into train, val, test.\n",
+    "    idx = np.random.permutation(len(D))\n",
+    "    train_size = int(0.8 * len(D))\n",
+    "    val_size = int(0.1 * len(D))\n",
+    "    train_idx = idx[:train_size]\n",
+    "    val_idx = idx[train_size: train_size + val_size]\n",
+    "    test_idx = idx[train_size + val_size:]\n",
+    "\n",
+    "    dataset_list = [D[train_idx], D[val_idx], D[test_idx]]\n",
+    "    return dataset_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ChoiceDataset(label=[], item_index=[10000], user_index=[10000], session_index=[10000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50], device=cuda:0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "dataset_1 = ChoiceDataset(user_index=user_index,\n",
+    "                        item_index=item_index,\n",
+    "                        session_index=session_index,\n",
+    "                        item_availability=None,  # everything is available.\n",
+    "                        # observables.\n",
+    "                        user_income=user_income.view(num_users, 1),\n",
+    "                        item_price=item_price.view(num_items, 1),\n",
+    "                        item_bin_cate=item_bin_cate).to(DEVICE)\n",
+    "\n",
+    "print(dataset_1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Fit A Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 100   \n",
+      "-----------------------------------\n",
+      "100       Trainable params\n",
+      "0         Non-trainable params\n",
+      "100       Total params\n",
+      "0.000     Total estimated model params size (MB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['beta_item'], 'observable': 'user_income'}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = beta_item * user_income\n",
+      "Total number of parameters: 100.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (beta_item): BayesianCoefficient(num_classes=50, dimension=1, prior=N(0, I))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.03\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50], device=cuda:0)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50], device=cuda:0)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50], device=cuda:0)\n",
+      "==================== train the model ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "`Trainer.fit` stopped: `max_epochs=3` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "time taken: 1.3115406036376953\n",
+      "==================== test performance ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.452           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -3.2950756352357566    </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.452          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -3.2950756352357566   \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# def fit_model(obs2prior: bool):\n",
+    "LATENT_DIM = 10  # the dimension of alpha and theta.\n",
+    "bemb = LitBEMBFlex(\n",
+    "    model_optimizer=\"Adam\",\n",
+    "    learning_rate=0.03,  # set the learning rate, feel free to play with different levels.\n",
+    "    pred_item=True,  # let the model predict item_index, don't change this one.\n",
+    "    num_seeds=128,  # number of Monte Carlo samples for estimating the ELBO.\n",
+    "    utility_formula='beta_item * user_income',  # the utility formula.\n",
+    "    num_users=num_users,\n",
+    "    num_items=num_items,\n",
+    "    trace_log_q=True,\n",
+    "    # whether to turn on obs2prior for each parameter.\n",
+    "    obs2prior_dict={'beta_item': False},\n",
+    "    # the dimension of beta_item, which is 1.\n",
+    "    coef_dim_dict={'beta_item': 1},\n",
+    ")\n",
+    "\n",
+    "# use GPU if available.\n",
+    "bemb = bemb.to(DEVICE)\n",
+    "    \n",
+    "# use the provided run helper to train the model.\n",
+    "# we set batch size to be 5% of the data size, and train the model for 10 epochs.\n",
+    "# there would be 20*10=200 gradient update steps in total.\n",
+    "bemb = bemb.fit_model(\n",
+    "    split_dataset_into_train_val_test(dataset_1),\n",
+    "    batch_size=256, num_epochs=3, num_workers=0, device=DEVICE, enable_progress_bar=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Comparison between $\\beta_i$ and $\\hat{\\beta}_i$ for items."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "real.shape=(50,), pred.shape=(50,)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 3000x1500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# actual beta_i's\n",
+    "real = beta_item.squeeze().numpy()\n",
+    "# prediction from the fitted variational distribution.\n",
+    "pred = bemb.state_dict()[\"coef_dict.beta_item.variational_mean_flexible\"].squeeze().numpy()\n",
+    "err = 1.96 * bemb.state_dict()[\"coef_dict.beta_item.variational_logstd\"].squeeze().exp()\n",
+    "\n",
+    "print(f\"{real.shape=:}, {pred.shape=:}\")\n",
+    "fig, ax = plt.subplots(figsize=(10, 5), dpi=DPI)\n",
+    "ax.scatter(np.arange(num_items), real, label=\"beta\", marker=\"o\", color=\"blue\")\n",
+    "ax.errorbar(np.arange(num_items), y=pred, yerr=err, label=\"beta-hat\", marker=\"x\", linestyle='none', color=\"orange\")\n",
+    "\n",
+    "ax.set_xlabel(\"Item Index\")\n",
+    "ax.set_ylabel(\"Real and Estimated Coefficients\")\n",
+    "ax.legend()\n",
+    "fig.savefig(os.path.join(OUTPUT_DIR, \"simulation_1_beta_hat.png\"), dpi=DPI, bbox_inches=\"tight\")\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Simulation Study 2: More Complicated Item-Specific Effects (Obs2Prior)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 2400x1800 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# modify the beta_item based on the item category.\n",
+    "for i in range(num_items):\n",
+    "    if item_bin_cate[i] == 1:\n",
+    "        beta_item[i] = beta_item[i] + 3\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(8, 6), dpi=DPI)\n",
+    "sns.regplot(x=item_price.squeeze().numpy(), y=beta_item.numpy(), ax=ax)\n",
+    "ax.set_xlabel(\"$price_i$\")\n",
+    "ax.set_ylabel(\"$beta_i$\")\n",
+    "fig.savefig(os.path.join(OUTPUT_DIR, \"simulation_2_income_coefficients.png\"), dpi=DPI, bbox_inches='tight')\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 1500/1500 [00:03<00:00, 375.69it/s]\n",
+      "100%|██████████| 10000/10000 [00:00<00:00, 27781.87it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# recompute the utility matrix using the new coefficient.\n",
+    "utility = torch.zeros(num_users, num_items, num_sessions)\n",
+    "for u in tqdm(range(num_users)):\n",
+    "    for i in range(num_items):\n",
+    "        for s in range(num_sessions):\n",
+    "            utility[u, i, s] = beta_item[i] * user_income[u]\n",
+    "# generate choices.\n",
+    "item_index = torch.empty(data_size, dtype=torch.long)\n",
+    "for idx in tqdm(range(data_size)):\n",
+    "    u = user_index[idx]\n",
+    "    s = session_index[idx]\n",
+    "    utility_list = utility[u, :, s]\n",
+    "    p = torch.softmax(utility_list, dim=0).numpy()\n",
+    "    item_index[idx] = np.random.choice(num_items, p=p)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Most bought item with their frequencies:\n",
+      "item\n",
+      "8       0.5743\n",
+      "2       0.0692\n",
+      "11      0.0554\n",
+      "1       0.0510\n",
+      "12      0.0446\n",
+      "dtype: float64\n",
+      "Least bought item with their frequencies:\n",
+      "item\n",
+      "24      0.0016\n",
+      "21      0.0013\n",
+      "9       0.0010\n",
+      "7       0.0010\n",
+      "15      0.0002\n",
+      "dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "report_most_least_bought_items(item_index)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset_2 = ChoiceDataset(user_index=user_index,\n",
+    "                        item_index=item_index,\n",
+    "                        session_index=session_index,\n",
+    "                        item_availability=None,  # everything is available.\n",
+    "                        # observables.\n",
+    "                        user_income=user_income.view(num_users, 1),\n",
+    "                        item_price=item_price.view(num_items, 1),\n",
+    "                        item_bin_cate=item_bin_cate.view(num_items, 1),\n",
+    "                        item_obs=item_obs\n",
+    "                        ).to(DEVICE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 104   \n",
+      "-----------------------------------\n",
+      "104       Trainable params\n",
+      "0         Non-trainable params\n",
+      "104       Total params\n",
+      "0.000     Total estimated model params size (MB)\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['beta_item'], 'observable': 'user_income'}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = beta_item * user_income\n",
+      "Total number of parameters: 104.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (beta_item): BayesianCoefficient(num_classes=50, dimension=1, prior=N(H*X_obs(H shape=torch.Size([1, 2]), X_obs shape=2), Ix1.0))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.3\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50, 1], item_obs=[50, 2], device=cuda:0)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50, 1], item_obs=[50, 2], device=cuda:0)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50, 1], item_obs=[50, 2], device=cuda:0)\n",
+      "==================== train the model ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "`Trainer.fit` stopped: `max_epochs=40` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "time taken: 15.171826839447021\n",
+      "==================== test performance ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.573           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -1.775816478602588     </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.573          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -1.775816478602588    \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "real.shape=(50,), pred.shape=(50,)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 100   \n",
+      "-----------------------------------\n",
+      "100       Trainable params\n",
+      "0         Non-trainable params\n",
+      "100       Total params\n",
+      "0.000     Total estimated model params size (MB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['beta_item'], 'observable': 'user_income'}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = beta_item * user_income\n",
+      "Total number of parameters: 100.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (beta_item): BayesianCoefficient(num_classes=50, dimension=1, prior=N(0, I))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.3\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50, 1], item_obs=[50, 2], device=cuda:0)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50, 1], item_obs=[50, 2], device=cuda:0)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_income=[1500, 1], item_price=[50, 1], item_bin_cate=[50, 1], item_obs=[50, 2], device=cuda:0)\n",
+      "==================== train the model ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "`Trainer.fit` stopped: `max_epochs=40` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "time taken: 13.723082304000854\n",
+      "==================== test performance ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.603           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">     -1.76185211494565     </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.603          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m    -1.76185211494565    \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "real.shape=(50,), pred.shape=(50,)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 3000x1500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 3000x1500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# run two versions of the model with and without obs2prior.\n",
+    "for enable_obs2prior in [True, False]:\n",
+    "    # def fit_model(obs2prior: bool):\n",
+    "    LATENT_DIM = 10  # the dimension of alpha and theta.\n",
+    "    bemb = LitBEMBFlex(\n",
+    "        model_optimizer=\"Adam\",\n",
+    "        learning_rate=0.3,  # set the learning rate, feel free to play with different levels.\n",
+    "        pred_item=True,  # let the model predict item_index, don't change this one.\n",
+    "        num_seeds=32,  # number of Monte Carlo samples for estimating the ELBO.\n",
+    "        utility_formula='beta_item * user_income',  # the utility formula.\n",
+    "        num_users=num_users,\n",
+    "        num_items=num_items,\n",
+    "        trace_log_q=True,\n",
+    "        # num_user_obs=dataset.user_obs.shape[1],\n",
+    "        num_item_obs=dataset_2.item_obs.shape[1],\n",
+    "        # whether to turn on obs2prior for each parameter.\n",
+    "        obs2prior_dict={'beta_item': enable_obs2prior},\n",
+    "        # the dimension of latents, since the utility is an inner product of theta and alpha, they should have\n",
+    "        # the same dimension.\n",
+    "        coef_dim_dict={'beta_item': 1},\n",
+    "    )\n",
+    "\n",
+    "    # use GPU if available.\n",
+    "    bemb = bemb.to(DEVICE)\n",
+    " \n",
+    "    # use the provided run helper to train the model.\n",
+    "    # we set batch size to be 5% of the data size, and train the model for 10 epochs.\n",
+    "    # there would be 20*10=200 gradient update steps in total.\n",
+    "    bemb = bemb.fit_model(split_dataset_into_train_val_test(dataset_2),\n",
+    "                          batch_size=128, num_epochs=40, num_workers=0, device=DEVICE, enable_progress_bar=False)\n",
+    "\n",
+    "    # plot the coefficients.\n",
+    "    real = beta_item.squeeze().numpy()\n",
+    "    pred = bemb.state_dict()[\"coef_dict.beta_item.variational_mean_flexible\"].squeeze().numpy()\n",
+    "    err = 1.96 * bemb.state_dict()[\"coef_dict.beta_item.variational_logstd\"].squeeze().exp()\n",
+    "\n",
+    "    print(f\"{real.shape=:}, {pred.shape=:}\")\n",
+    "    fig, ax = plt.subplots(figsize=(10, 5), dpi=DPI)\n",
+    "    ax.scatter(np.arange(num_items), real, label=\"beta\", marker=\"o\")\n",
+    "    ax.scatter(np.arange(num_items), pred, label=\"beta-hat\", marker=\"x\")\n",
+    "    ax.errorbar(np.arange(num_items), y=pred, yerr=err, label=\"beta-hat\", marker=\"x\", linestyle='none', color=\"orange\")\n",
+    "    ax.set_xlabel(\"Item Index\")\n",
+    "    ax.set_ylabel(\"Real and Estimated Coefficients\")\n",
+    "    ax.legend()\n",
+    "\n",
+    "    if enable_obs2prior:\n",
+    "        ax.set_title(\"Item-Specific Coefficients with Obs2Prior\")\n",
+    "    else:\n",
+    "        ax.set_title(\"Item-Specific Coefficients without Obs2Prior\")\n",
+    "    fig.savefig(os.path.join(OUTPUT_DIR, f\"simulation_2_beta_hat_obs2prior={enable_obs2prior}.png\"), dpi=DPI, bbox_inches=\"tight\")\n",
+    "    fig.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Simulation Study 3: User Latent and Item Latent Interactions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## User Specific Preferences"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 2400x900 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "Is = np.sin(np.arange(int(0.8*num_users)) / num_users * 4 * np.pi)\n",
+    "Is = (Is + 1) / 2 * num_items\n",
+    "Is = Is.astype(int)\n",
+    "\n",
+    "Us = np.arange(num_users)\n",
+    "Is = np.concatenate([\n",
+    "    np.arange(int(0.2*num_users)) * num_items / (0.2*num_users),\n",
+    "    Is\n",
+    "])\n",
+    "\n",
+    "PREFERENCE = dict((u, i) for (u, i) in zip(Us, Is))\n",
+    "\n",
+    "# plot the preference\n",
+    "fig, ax = plt.subplots(figsize=(8, 3), dpi=DPI)\n",
+    "ax.scatter(Us, Is, s=0.3)\n",
+    "ax.set_xlabel('User Index')\n",
+    "ax.set_ylabel('Item Index $i^{like}(u)$')\n",
+    "fig.savefig(os.path.join(OUTPUT_DIR, \"simulation_3_user_preferences.png\"), dpi=DPI, bbox_inches='tight')\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "item_index = torch.LongTensor(np.random.choice(num_items, size=data_size))\n",
+    "user_bin_cate = torch.zeros(num_users).long()\n",
+    "# group users into two categories.\n",
+    "user_bin_cate[:100] = 1\n",
+    "user_bin_cate[200:num_users // 2] = 1\n",
+    "\n",
+    "for idx in range(data_size):\n",
+    "    # follows random behaviors.\n",
+    "    rnd = np.random.rand()\n",
+    "    if user_bin_cate[int(user_index[idx])] == 0:\n",
+    "        if rnd <= 0.5:\n",
+    "            # choose based on preference with a probability of 0.5.\n",
+    "            item_index[idx] = PREFERENCE[int(user_index[idx])]\n",
+    "    else:\n",
+    "        if rnd <= 0.5:\n",
+    "            # choose based on preference with a probability of 0.5.\n",
+    "            item_index[idx] = num_items - PREFERENCE[int(user_index[idx])] - 1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To have a visual inspection on the preference we added, we can plot a heat map indexed by (user, item) and visualize the frequency of bought items by each user. In the heat map below, each row represents the empirical distribution of items (x-axis) bought. Warmer color (red) indicates high purchasing frequencies, which shows the synthetic sin-curve of preference we enforced above."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_22399/2592746616.py:2: FutureWarning: In a future version of pandas all arguments of DataFrame.pivot will be keyword-only.\n",
+      "  df = df.pivot('item', 'user', 'size').fillna(0.0)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1800x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df = pd.DataFrame(data={'item': item_index, 'user': user_index}).groupby(['item', 'user']).size().rename('size').reset_index()\n",
+    "df = df.pivot('item', 'user', 'size').fillna(0.0)\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(18, 3))\n",
+    "sns.heatmap(df.values, square=False, ax=ax, cmap='coolwarm')\n",
+    "ax.set(xlabel='User Index', ylabel='Item Selected')\n",
+    "fig.savefig(os.path.join(OUTPUT_DIR, \"simulation_3_heatmap.png\"), dpi=DPI, bbox_inches=\"tight\")\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "No `session_index` is provided, assume each choice instance is in its own session.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# user_obs = torch.eye(num_users)\n",
+    "# user_obs = user_bin_cate.view(-1, 1)\n",
+    "# user_obs = torch.zeros(num_users, num_items)\n",
+    "# for u in range(num_users):\n",
+    "#     x = int(PREFERENCE[u])\n",
+    "#     if user_bin_cate[u] == 0:\n",
+    "#         user_obs[u, x] = 1\n",
+    "#     else:\n",
+    "#         user_obs[u, num_items - x - 1] = 1\n",
+    "# user_obs[torch.arange(num_users), Is] = 1\n",
+    "dataset_3 = ChoiceDataset(user_index=user_index, item_index=item_index, user_obs=torch.eye(num_users))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fit_model(obs2prior: bool):\n",
+    "    LATENT_DIM = 5  # the dimension of alpha and theta.\n",
+    "    bemb = LitBEMBFlex(\n",
+    "        learning_rate=0.03,  # set the learning rate, feel free to play with different levels.\n",
+    "        pred_item=True,  # let the model predict item_index, don't change this one.\n",
+    "        num_seeds=32,  # number of Monte Carlo samples for estimating the ELBO.\n",
+    "        utility_formula='theta_user * alpha_item',  # the utility formula.\n",
+    "        num_users=num_users,\n",
+    "        num_items=num_items,\n",
+    "        num_user_obs=dataset_3.user_obs.shape[1],\n",
+    "        # whether to turn on obs2prior for each parameter.\n",
+    "        obs2prior_dict={'theta_user': obs2prior, 'alpha_item': False},\n",
+    "        # the dimension of latents, since the utility is an inner product of theta and alpha, they should have\n",
+    "        # the same dimension.\n",
+    "        coef_dim_dict={'theta_user': LATENT_DIM, 'alpha_item': LATENT_DIM}\n",
+    "    )\n",
+    "\n",
+    "    # use GPU if available.\n",
+    "    if torch.cuda.is_available():\n",
+    "        bemb = bemb.to('cuda')\n",
+    "       \n",
+    "    # use the provided run helper to train the model.\n",
+    "    # we set batch size to be 5% of the data size, and train the model for 10 epochs.\n",
+    "    # there would be 20*10=200 gradient update steps in total.\n",
+    "    bemb = bemb.fit_model(split_dataset_into_train_val_test(dataset_3),\n",
+    "                          batch_size=128, num_epochs=100, num_workers=0, device=DEVICE, enable_progress_bar=False)\n",
+    "\n",
+    "    # visualize the prediction.\n",
+    "    T = bemb.model.coef_dict['theta_user'].variational_mean_flexible.data\n",
+    "    A = bemb.model.coef_dict['alpha_item'].variational_mean_flexible.data\n",
+    "    fig, ax = plt.subplots(figsize=(18, 3))\n",
+    "    sns.heatmap((A @ T.T).numpy(), square=False, ax=ax, cmap='coolwarm')\n",
+    "    if obs2prior:\n",
+    "        ax.set_title(\"User-Item Interaction Utility with Obs2Prior\")\n",
+    "    else:\n",
+    "        ax.set_title(\"User-Item Interaction Utility without Obs2Prior\")\n",
+    "    fig.savefig(os.path.join(OUTPUT_DIR, f\"simulation_3_interaction_hat_obs2prior={obs2prior}.png\"), dpi=DPI, bbox_inches=\"tight\")\n",
+    "    fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 30.5 K\n",
+      "-----------------------------------\n",
+      "30.5 K    Trainable params\n",
+      "0         Non-trainable params\n",
+      "30.5 K    Total params\n",
+      "0.122     Total estimated model params size (MB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['theta_user', 'alpha_item'], 'observable': None}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = theta_user * alpha_item\n",
+      "Total number of parameters: 30500.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (theta_user): BayesianCoefficient(num_classes=1500, dimension=5, prior=N(H*X_obs(H shape=torch.Size([5, 1500]), X_obs shape=1500), Ix1.0))\n",
+      "  (alpha_item): BayesianCoefficient(num_classes=50, dimension=5, prior=N(0, I))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.03\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[], user_obs=[1500, 1500], device=cpu)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_obs=[1500, 1500], device=cpu)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_obs=[1500, 1500], device=cpu)\n",
+      "==================== train the model ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "`Trainer.fit` stopped: `max_epochs=100` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "time taken: 62.982523918151855\n",
+      "==================== test performance ====================\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.284           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -4.053789083855227     </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.284          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -4.053789083855227    \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1800x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fit_model(obs2prior=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 15.5 K\n",
+      "-----------------------------------\n",
+      "15.5 K    Trainable params\n",
+      "0         Non-trainable params\n",
+      "15.5 K    Total params\n",
+      "0.062     Total estimated model params size (MB)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['theta_user', 'alpha_item'], 'observable': None}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = theta_user * alpha_item\n",
+      "Total number of parameters: 15500.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (theta_user): BayesianCoefficient(num_classes=1500, dimension=5, prior=N(0, I))\n",
+      "  (alpha_item): BayesianCoefficient(num_classes=50, dimension=5, prior=N(0, I))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.03\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[], user_obs=[1500, 1500], device=cpu)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_obs=[1500, 1500], device=cpu)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_obs=[1500, 1500], device=cpu)\n",
+      "==================== train the model ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "`Trainer.fit` stopped: `max_epochs=100` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "time taken: 58.35726451873779\n",
+      "==================== test performance ====================\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.042           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -3.9120112688541413    </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.042          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -3.9120112688541413   \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1800x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fit_model(obs2prior=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Simulation Study 4: User Latent and Item Latent Coefficient"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "magnitude = 5\n",
+    "theta = torch.empty(num_users, num_items)\n",
+    "for u in range(num_users):\n",
+    "    for i in range(num_items):\n",
+    "        diff = np.abs(i - (PREFERENCE[u])) / 100\n",
+    "        theta[u, i] = 1/(1 + np.exp(-diff))\n",
+    "        theta[u, i] = magnitude * theta[u, i] - 2.8"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1800x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, ax = plt.subplots(figsize=(18, 3))\n",
+    "sns.heatmap(theta.T, square=False, ax=ax, cmap='coolwarm')\n",
+    "ax.set(xlabel='User Index', ylabel='Item Index')\n",
+    "fig.savefig(os.path.join(OUTPUT_DIR, \"simulation_4_coefficients.png\"), dpi=DPI, bbox_inches=\"tight\")\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# generate random session observables.\n",
+    "session_obs = (torch.randn(num_sessions) + 1) * 100"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 1500/1500 [00:04<00:00, 330.78it/s]\n",
+      "100%|██████████| 10000/10000 [00:00<00:00, 27669.54it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Most bought item with their frequencies:\n",
+      "item\n",
+      "0       0.4339\n",
+      "49      0.2849\n",
+      "1       0.0736\n",
+      "48      0.0544\n",
+      "2       0.0227\n",
+      "dtype: float64\n",
+      "Least bought item with their frequencies:\n",
+      "item\n",
+      "19      0.0013\n",
+      "16      0.0013\n",
+      "11      0.0012\n",
+      "9       0.0012\n",
+      "24      0.0011\n",
+      "dtype: float64\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# recompute utilities.\n",
+    "utility = torch.zeros(num_users, num_items, num_sessions)\n",
+    "for u in tqdm(range(num_users)):\n",
+    "    for i in range(num_items):\n",
+    "        for s in range(num_sessions):\n",
+    "            utility[u, i, s] = theta[u, i] * session_obs[s]\n",
+    "\n",
+    "# sample random choices as before.\n",
+    "item_index = torch.empty(data_size, dtype=torch.long)\n",
+    "for idx in tqdm(range(data_size)):\n",
+    "    u = user_index[idx]\n",
+    "    s = session_index[idx]\n",
+    "    utility_list = utility[u, :, s]\n",
+    "    p = torch.softmax(utility_list, dim=0).numpy()\n",
+    "    item_chosen = np.random.choice(num_items, p=p)\n",
+    "    item_index[idx] = item_chosen\n",
+    "\n",
+    "# report most bought and least bought items.\n",
+    "report_most_least_bought_items(item_index)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_obs = torch.zeros(num_users, num_items)\n",
+    "user_obs[torch.arange(num_users), Is] = 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset_4 = ChoiceDataset(\n",
+    "    user_index=user_index,\n",
+    "    item_index=item_index,\n",
+    "    user_obs=user_obs,\n",
+    "    item_obs=item_obs,\n",
+    "    session_index=session_index,\n",
+    "    session_obs=session_obs.view(num_sessions, 1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fit_model(obs2prior: bool):\n",
+    "    LATENT_DIM = 5  # the dimension of alpha and theta.\n",
+    "    bemb = LitBEMBFlex(\n",
+    "        learning_rate=0.03,  # set the learning rate, feel free to play with different levels.\n",
+    "        pred_item=True,  # let the model predict item_index, don't change this one.\n",
+    "        num_seeds=32,  # number of Monte Carlo samples for estimating the ELBO.\n",
+    "        utility_formula='theta_user * alpha_item * session_obs',  # the utility formula.\n",
+    "        num_users=num_users,\n",
+    "        num_items=num_items,\n",
+    "        num_sessions=num_sessions,\n",
+    "        num_user_obs=dataset_4.user_obs.shape[1],\n",
+    "        # whether to turn on obs2prior for each parameter.\n",
+    "        obs2prior_dict={'theta_user': obs2prior, 'alpha_item': False},\n",
+    "        # the dimension of latents, since the utility is an inner product of theta and alpha, they should have\n",
+    "        # the same dimension.\n",
+    "        coef_dim_dict={'theta_user': LATENT_DIM, 'alpha_item': LATENT_DIM}\n",
+    "    ).to(DEVICE)\n",
+    "       \n",
+    "    # use the provided run helper to train the model.\n",
+    "    # we set batch size to be 5% of the data size, and train the model for 10 epochs.\n",
+    "    # there would be 20*10=200 gradient update steps in total.\n",
+    "    bemb = bemb.fit_model(split_dataset_into_train_val_test(dataset_4),\n",
+    "                          batch_size=128, num_epochs=300, num_workers=0, device=DEVICE, enable_progress_bar=False)\n",
+    "\n",
+    "    # visualize the prediction.\n",
+    "    T = bemb.model.coef_dict['theta_user'].variational_mean_flexible.data\n",
+    "    A = bemb.model.coef_dict['alpha_item'].variational_mean_flexible.data\n",
+    "    fig, ax = plt.subplots(figsize=(18, 3))\n",
+    "    sns.heatmap((A @ T.T).numpy(), square=False, ax=ax, cmap='coolwarm')\n",
+    "    if obs2prior:\n",
+    "        ax.set_title(\"User-Item Interaction Utility with Obs2Prior\")\n",
+    "    else:\n",
+    "        ax.set_title(\"User-Item Interaction Utility without Obs2Prior\")\n",
+    "    fig.savefig(os.path.join(OUTPUT_DIR, f\"simulation_4_interaction_hat_obs2prior={obs2prior}.png\"), dpi=DPI, bbox_inches=\"tight\")\n",
+    "    fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "GPU available: True (cuda), used: True\n",
+      "TPU available: False, using: 0 TPU cores\n",
+      "IPU available: False, using: 0 IPUs\n",
+      "HPU available: False, using: 0 HPUs\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "\n",
+      "  | Name  | Type     | Params\n",
+      "-----------------------------------\n",
+      "0 | model | BEMBFlex | 16.0 K\n",
+      "-----------------------------------\n",
+      "16.0 K    Trainable params\n",
+      "0         Non-trainable params\n",
+      "16.0 K    Total params\n",
+      "0.064     Total estimated model params size (MB)\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BEMB: utility formula parsed:\n",
+      "[{'coefficient': ['theta_user', 'alpha_item'], 'observable': 'session_obs'}]\n",
+      "==================== model received ====================\n",
+      "Bayesian EMBedding Model with U[user, item, session] = theta_user * alpha_item * session_obs\n",
+      "Total number of parameters: 16000.\n",
+      "With the following coefficients:\n",
+      "ModuleDict(\n",
+      "  (theta_user): BayesianCoefficient(num_classes=1500, dimension=5, prior=N(H*X_obs(H shape=torch.Size([5, 50]), X_obs shape=50), Ix1.0))\n",
+      "  (alpha_item): BayesianCoefficient(num_classes=50, dimension=5, prior=N(0, I))\n",
+      ")\n",
+      "[]\n",
+      "Optimizer: Adam, Learning rate: 0.03\n",
+      "==================== data set received ====================\n",
+      "[Training dataset] ChoiceDataset(label=[], item_index=[8000], user_index=[8000], session_index=[8000], item_availability=[], user_obs=[1500, 50], item_obs=[50, 2], session_obs=[10, 1], device=cpu)\n",
+      "[Validation dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_obs=[1500, 50], item_obs=[50, 2], session_obs=[10, 1], device=cpu)\n",
+      "[Testing dataset] ChoiceDataset(label=[], item_index=[1000], user_index=[1000], session_index=[1000], item_availability=[], user_obs=[1500, 50], item_obs=[50, 2], session_obs=[10, 1], device=cpu)\n",
+      "==================== train the model ====================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "`Trainer.fit` stopped: `max_epochs=300` reached.\n",
+      "You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision\n",
+      "LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n",
+      "/home/tianyudu/anaconda3/envs/dev/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, test_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.\n",
+      "  rank_zero_warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "time taken: 147.24073934555054\n",
+      "==================== test performance ====================\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">         test_acc          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">           0.711           </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\">          test_ll          </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    -1.0611618126890972    </span>│\n",
+       "└───────────────────────────┴───────────────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36m        test_acc         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m          0.711          \u001b[0m\u001b[35m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m         test_ll         \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   -1.0611618126890972   \u001b[0m\u001b[35m \u001b[0m│\n",
+       "└───────────────────────────┴───────────────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1800x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fit_model(obs2prior=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "dev",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": true
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/tutorials/supermarket/configs.yaml b/tutorials/supermarket/configs.yaml
index ce6b672..7ecc4f7 100644
--- a/tutorials/supermarket/configs.yaml
+++ b/tutorials/supermarket/configs.yaml
@@ -1,30 +1,36 @@
 device: cuda
 # data_dir: /home/tianyudu/Data/MoreSupermarket/tsv/
-data_dir: /home/tianyudu/Data/MoreSupermarket/20180101-20191231_13/tsv/
+# data_dir: /home/tianyudu/Data/MoreSupermarket/20180101-20191231_13/tsv/
+data_dir: /oak/stanford/groups/athey/MoreSupermarkets/csv/new_data/nf_runs/1904/20180101-20191231_44/tsv
 # utility: lambda_item
 # utility: lambda_item + theta_user * alpha_item
 # utility: lambda_item + theta_user * alpha_item + zeta_user * item_obs
-utility: lambda_item + theta_user * alpha_item + gamma_user * beta_item * price_obs
+# utility: lambda_item + theta_user * alpha_item + gamma_user * beta_item * price_obs
+utility: lambda_item + theta_user * alpha_item + gamma_user * price_obs
+# utility: alpha_item * gamma_user * price_obs
 out_dir: ./output/
 # model configuration.
+coef_dist_dict:
+  default: 'gaussian'
+  gamma_user: 'gamma'
 obs2prior_dict:
-  lambda_item: True
-  theta_user: True
-  alpha_item: True
+  lambda_item: False
+  theta_user: False
+  alpha_item: False
   zeta_user: True
   lota_item: True
-  gamma_user: True
+  gamma_user: False
   beta_item: True
 coef_dim_dict:
   lambda_item: 1
   theta_user: 10
   alpha_item: 10
-  gamma_user: 10
-  beta_item: 10
+  gamma_user: 1
+  beta_item: 1
 #### optimization.
 trace_log_q: False
 shuffle: False
 batch_size: 100000
-num_epochs: 3
+num_epochs: 100
 learning_rate: 0.03
-num_mc_seeds: 1
+num_mc_seeds: 2
diff --git a/tutorials/supermarket/main.py b/tutorials/supermarket/main.py
index 9653bfd..b7c9548 100644
--- a/tutorials/supermarket/main.py
+++ b/tutorials/supermarket/main.py
@@ -10,7 +10,8 @@
 from termcolor import cprint
 from example_customized_module import ExampleCustomizedModule
 from torch_choice.data import ChoiceDataset
-from bemb.model import LitBEMBFlex
+# from bemb.model import LitBEMBFlex
+from bemb.model.bemb_supermarket_lightning import LitBEMBFlex
 from bemb.utils.run_helper import run
 
 
@@ -21,7 +22,6 @@ def load_configs(yaml_file: str):
     defaults = {
         'num_verify_val': 10,
         'early_stopping': {'validation_llh_flat': -1},
-        'write_best_model': True
         'write_best_model': True,
         'pred_item' : True,
     }
@@ -71,28 +71,30 @@ def load_tsv(file_name, data_dir):
     # ==============================================================================================
     # user observables
     # ==============================================================================================
-    user_obs = pd.read_csv(os.path.join(configs.data_dir, 'obsUser.tsv'),
-                           sep='\t',
-                           index_col=0,
-                           header=None)
-    # TODO(Tianyu): there could be duplicate information for each user.
-    # do we need to catch it in some check process?
-    user_obs = user_obs.groupby(user_obs.index).first().sort_index()
-    user_obs = torch.Tensor(user_obs.values)
-    configs.num_user_obs = user_obs.shape[1]
-    configs.coef_dim_dict['obsuser_item'] = configs.num_user_obs
+    if configs.obs_user:
+        user_obs = pd.read_csv(os.path.join(configs.data_dir, 'obsUser.tsv'),
+                               sep='\t',
+                               index_col=0,
+                               header=None)
+        # TODO(Tianyu): there could be duplicate information for each user.
+        # do we need to catch it in some check process?
+        user_obs = user_obs.groupby(user_obs.index).first().sort_index()
+        user_obs = torch.Tensor(user_obs.values)
+        configs.num_user_obs = user_obs.shape[1]
+        configs.coef_dim_dict['obsuser_item'] = configs.num_user_obs
 
     # ==============================================================================================
     # item observables
     # ==============================================================================================
-    item_obs = pd.read_csv(os.path.join(configs.data_dir, 'obsItem.tsv'),
-                           sep='\t',
-                           index_col=0,
-                           header=None)
-    item_obs = item_obs.groupby(item_obs.index).first().sort_index()
-    item_obs = torch.Tensor(item_obs.values)
-    configs.num_item_obs = item_obs.shape[1]
-    configs.coef_dim_dict['obsitem_user'] = configs.num_item_obs
+    if configs.obs_item:
+        item_obs = pd.read_csv(os.path.join(configs.data_dir, 'obsItem.tsv'),
+                               sep='\t',
+                               index_col=0,
+                               header=None)
+        item_obs = item_obs.groupby(item_obs.index).first().sort_index()
+        item_obs = torch.Tensor(item_obs.values)
+        configs.num_item_obs = item_obs.shape[1]
+        configs.coef_dim_dict['obsitem_user'] = configs.num_item_obs
 
     # ==============================================================================================
     # item availability
@@ -153,14 +155,22 @@ def load_tsv(file_name, data_dir):
         # example day of week, random example.
         session_day_of_week = torch.LongTensor(np.random.randint(0, 7, configs.num_sessions))
 
-        choice_dataset = ChoiceDataset(item_index=label,
-                                       user_index=user_index,
-                                       session_index=session_index,
-                                       item_availability=item_availability,
-                                       user_obs=user_obs,
-                                       item_obs=item_obs,
-                                       price_obs=price_obs,
-                                       session_day_of_week=session_day_of_week)
+        choice_dataset_args = {
+            "item_index": label,
+            "user_index": user_index,
+            "session_index": session_index,
+            "item_availability": item_availability,
+            "price_obs": price_obs,
+            "session_day_of_week": session_day_of_week
+               }
+
+        if configs.obs_user:
+            choice_dataset_args["user_obs"] = user_obs
+
+        if configs.obs_item:
+            choice_dataset_args["item_obs"] = item_obs
+
+        choice_dataset = ChoiceDataset(**choice_dataset_args)
 
         dataset_list.append(choice_dataset)
 
@@ -195,9 +205,19 @@ def load_tsv(file_name, data_dir):
     # ==============================================================================================
     # pytorch-lightning training
     # ==============================================================================================
+    # if prior_mean is in the configs namespace set it to the prior mean
+    if hasattr(configs, 'prior_mean'):
+        prior_mean = configs.prior_mean
+    else:
+        prior_mean = 0.0
+    if hasattr(configs, 'prior_variance'):
+        prior_variance = configs.prior_variance
+    else:
+        prior_variance = 1.0
     bemb = LitBEMBFlex(
         # trainings args.
         pred_item = configs.pred_item,
+        coef_dist_dict=configs.coef_dist_dict,
         learning_rate=configs.learning_rate,
         num_seeds=configs.num_mc_seeds,
         # model args, will be passed to BEMB constructor.
@@ -209,14 +229,30 @@ def load_tsv(file_name, data_dir):
         coef_dim_dict=configs.coef_dim_dict,
         trace_log_q=configs.trace_log_q,
         category_to_item=category_to_item,
-        num_user_obs=configs.num_user_obs,
-        num_item_obs=configs.num_item_obs,
-        # num_price_obs=configs.num_price_obs,
+        num_user_obs=configs.num_user_obs if configs.obs_user else None,
+        num_item_obs=configs.num_item_obs if configs.obs_item else None,
+        prior_mean = prior_mean,
+        prior_variance= prior_variance,
+        num_price_obs=configs.num_price_obs,
+        preprocess=False,
         # additional_modules=[ExampleCustomizedModule()]
     )
 
     bemb = bemb.to(configs.device)
-    bemb = run(bemb, dataset_list, batch_size=configs.batch_size, num_epochs=configs.num_epochs)
+    bemb = run(bemb, dataset_list, batch_size=configs.batch_size, num_epochs=configs.num_epochs, run_test=False)
+
+    # '''
+    # coeffs = coeffs**2
+    # give distribution statistics
+    if 'gamma_user' in configs.utility:
+        coeffs_gamma = bemb.model.coef_dict['gamma_user'].variational_mean.detach().cpu().numpy()
+        print('Coefficients statistics Gamma:')
+        print(pd.DataFrame(coeffs_gamma).describe())
+    if 'nfact_category' in configs.utility:
+        coeffs_nfact = bemb.model.coef_dict['nfact_category'].variational_mean.detach().cpu().numpy()
+        print('Coefficients statistics nfact_category:')
+        print(pd.DataFrame(coeffs_nfact).describe())
+    # '''
 
     # ==============================================================================================
     # inference example
diff --git a/tutorials/supermarket/main_shopper.py b/tutorials/supermarket/main_shopper.py
new file mode 100644
index 0000000..7bbb1e4
--- /dev/null
+++ b/tutorials/supermarket/main_shopper.py
@@ -0,0 +1,227 @@
+import argparse
+import os
+import sys
+
+import numpy as np
+import pandas as pd
+import torch
+import yaml
+from sklearn.preprocessing import LabelEncoder
+from termcolor import cprint
+from example_customized_module import ExampleCustomizedModule
+from torch_choice.data import ChoiceDataset
+from bemb.model import LitBEMBFlex
+from bemb.utils.run_helper import run
+
+
+def load_configs(yaml_file: str):
+    with open(yaml_file, 'r') as file:
+        data_loaded = yaml.safe_load(file)
+    # Add defaults
+    defaults = {
+        'num_verify_val': 10,
+        'early_stopping': {'validation_llh_flat': -1},
+        'write_best_model': True,
+        'pred_item' : True,
+    }
+    defaults.update(data_loaded)
+    configs = argparse.Namespace(**defaults)
+    return configs
+
+
+def is_sorted(x):
+    return all(x == np.sort(x))
+
+
+def load_tsv(file_name, data_dir):
+    return pd.read_csv(os.path.join(data_dir, file_name),
+                       sep='\t',
+                       index_col=None,
+                       names=['user_id', 'item_id', 'session_id', 'quantity'])
+
+
+if __name__ == '__main__':
+    cprint('Your are running an example script.', 'green')
+    # sys.argv[1] should be the yaml file.
+    configs = load_configs(sys.argv[1])
+
+    # ==============================================================================================
+    # Load standard BEMB inputs.
+    # ==============================================================================================
+    train = load_tsv('train.tsv', configs.data_dir)
+    # read standard BEMB input files.
+    validation = load_tsv('validation.tsv', configs.data_dir)
+    test = load_tsv('test.tsv', configs.data_dir)
+
+    # ==============================================================================================
+    # Encode users and items to {0, 1, ..., num-1}.
+    # ==============================================================================================
+    # combine data for encoding.
+    data_all = pd.concat([train, validation, test], axis=0)
+    # encode user.
+    user_encoder = LabelEncoder().fit(data_all['user_id'].values)
+    configs.num_users = len(user_encoder.classes_)
+    assert is_sorted(user_encoder.classes_)
+    # encode items.
+    item_encoder = LabelEncoder().fit(data_all['item_id'].values)
+    configs.num_items = len(item_encoder.classes_)
+    assert is_sorted(item_encoder.classes_)
+
+    # ==============================================================================================
+    # user observables
+    # ==============================================================================================
+    user_obs = pd.read_csv(os.path.join(configs.data_dir, 'obsUser.tsv'),
+                           sep='\t',
+                           index_col=0,
+                           header=None)
+    # TODO(Tianyu): there could be duplicate information for each user.
+    # do we need to catch it in some check process?
+    user_obs = user_obs.groupby(user_obs.index).first().sort_index()
+    user_obs = torch.Tensor(user_obs.values)
+    configs.num_user_obs = user_obs.shape[1]
+    configs.coef_dim_dict['obsuser_item'] = configs.num_user_obs
+
+    # ==============================================================================================
+    # item observables
+    # ==============================================================================================
+    item_obs = pd.read_csv(os.path.join(configs.data_dir, 'obsItem.tsv'),
+                           sep='\t',
+                           index_col=0,
+                           header=None)
+    item_obs = item_obs.groupby(item_obs.index).first().sort_index()
+    item_obs = torch.Tensor(item_obs.values)
+    configs.num_item_obs = item_obs.shape[1]
+    configs.coef_dim_dict['obsitem_user'] = configs.num_item_obs
+
+    # ==============================================================================================
+    # item availability
+    # ==============================================================================================
+    # parse item availability.
+    # Try and catch? Optionally specify full availability?
+    a_tsv = pd.read_csv(os.path.join(configs.data_dir, 'availabilityList.tsv'),
+                        sep='\t',
+                        index_col=None,
+                        header=None,
+                        names=['session_id', 'item_id'])
+
+    # availability ties session as well.
+    session_encoder = LabelEncoder().fit(a_tsv['session_id'].values)
+    configs.num_sessions = len(session_encoder.classes_)
+    assert is_sorted(session_encoder.classes_)
+    # this loop could be slow, depends on # sessions.
+    item_availability = torch.zeros(configs.num_sessions, configs.num_items).bool()
+
+    a_tsv['item_id'] = item_encoder.transform(a_tsv['item_id'].values)
+    a_tsv['session_id'] = session_encoder.transform(a_tsv['session_id'].values)
+
+    for session_id, df_group in a_tsv.groupby('session_id'):
+        # get IDs of items available at this date.
+        a_item_ids = df_group['item_id'].unique()  # this unique is not necessary if the dataset is well-prepared.
+        item_availability[session_id, a_item_ids] = True
+
+    # ==============================================================================================
+    # price observables
+    # ==============================================================================================
+    df_price = pd.read_csv(os.path.join(configs.data_dir, 'item_sess_price.tsv'),
+                           sep='\t',
+                           names=['item_id', 'session_id', 'price'])
+
+    # only keep prices of relevant items.
+    mask = df_price['item_id'].isin(item_encoder.classes_)
+    df_price = df_price[mask]
+
+    df_price['item_id'] = item_encoder.transform(df_price['item_id'].values)
+    df_price['session_id'] = session_encoder.transform(df_price['session_id'].values)
+    df_price = df_price.pivot(index='session_id', columns='item_id')
+    # NAN prices.
+    df_price.fillna(0.0, inplace=True)
+    price_obs = torch.Tensor(df_price.values).view(configs.num_sessions, configs.num_items, 1)
+    configs.num_price_obs = 1
+
+    # ==============================================================================================
+    # create datasets
+    # ==============================================================================================
+    dataset_list = list()
+    for d in (train, validation, test):
+        user_index = torch.LongTensor(user_encoder.transform(d['user_id'].values))
+        label = torch.LongTensor(item_encoder.transform(d['item_id'].values))
+        session_index = torch.LongTensor(session_encoder.transform(d['session_id'].values))
+        # get the date (aka session_id in the raw dataset) of each row in the dataset, retrieve
+        # the item availability information from that date.
+
+        # example day of week, random example.
+        session_day_of_week = torch.LongTensor(np.random.randint(0, 7, configs.num_sessions))
+
+        choice_dataset = ChoiceDataset(item_index=label,
+                                       user_index=user_index,
+                                       session_index=session_index,
+                                       item_availability=item_availability,
+                                       user_obs=user_obs,
+                                       item_obs=item_obs,
+                                       price_obs=price_obs,
+                                       session_day_of_week=session_day_of_week)
+
+        dataset_list.append(choice_dataset)
+
+    # ==============================================================================================
+    # category information
+    # ==============================================================================================
+    item_groups = pd.read_csv(os.path.join(configs.data_dir, 'itemGroup.tsv'),
+                              sep='\t',
+                              index_col=None,
+                              names=['item_id', 'category_id'])
+
+    # TODO(Tianyu): handle duplicate group information.
+    item_groups = item_groups.groupby('item_id').first().reset_index()
+    # filter out items never purchased.
+    mask = item_groups['item_id'].isin(item_encoder.classes_)
+    item_groups = item_groups[mask].reset_index(drop=True)
+    item_groups = item_groups.sort_values(by='item_id')
+
+    category_encoder = LabelEncoder().fit(item_groups['category_id'])
+    configs.num_categories = len(category_encoder.classes_)
+
+    # encode them to consecutive integers {0, ..., num_items-1}.
+    item_groups['item_id'] = item_encoder.transform(
+        item_groups['item_id'].values)
+    item_groups['category_id'] = category_encoder.transform(
+        item_groups['category_id'].values)
+
+    print('Category sizes:')
+    print(item_groups.groupby('category_id').size().describe())
+    item_groups = item_groups.groupby('category_id')['item_id'].apply(list)
+    category_to_item = dict(zip(item_groups.index, item_groups.values))
+    # ==============================================================================================
+    # pytorch-lightning training
+    # ==============================================================================================
+    bemb = LitBEMBFlex(
+        # trainings args.
+        pred_item = configs.pred_item,
+        learning_rate=configs.learning_rate,
+        num_seeds=configs.num_mc_seeds,
+        # model args, will be passed to BEMB constructor.
+        utility_formula=configs.utility,
+        num_users=configs.num_users,
+        num_items=configs.num_items,
+        num_sessions=configs.num_sessions,
+        obs2prior_dict=configs.obs2prior_dict,
+        coef_dim_dict=configs.coef_dim_dict,
+        trace_log_q=configs.trace_log_q,
+        category_to_item=category_to_item,
+        num_user_obs=configs.num_user_obs,
+        num_item_obs=configs.num_item_obs,
+        # num_price_obs=configs.num_price_obs,
+        # additional_modules=[ExampleCustomizedModule()]
+    )
+
+    bemb = bemb.to(configs.device)
+    bemb = run(bemb, dataset_list, batch_size=configs.batch_size, num_epochs=configs.num_epochs)
+
+    # ==============================================================================================
+    # inference example
+    # ==============================================================================================
+    with torch.no_grad():
+        # disable gradient tracking to save computational cost.
+        utility_chosen = bemb.model(dataset_list[2], return_type='utility', return_scope='item_index')
+        # uses much higher memory!
+        # utility_all = bemb.model(dataset_list[2], return_logit=True, all_items=True)