Info update

CV, pub info, and about me changed

home/index.xml

@@ -28,7 +28,7 @@
       <pubDate>Wed, 20 Apr 2016 00:00:00 -0400</pubDate>
 
       <guid>/home/about/</guid>
-      <description>About In my research I use insights from nonparametric and functional data analysis to devise new, rigorously guaranteed methods for solving dynamic economic models with infinite dimensional uncertainty and apply these methods to understand the dynamics of economic heterogeneity in a variety of contexts.</description>
+      <description>About In my research I combine approaches from Econometrics, Machine Learning, and High-dimensional Statistics to devise performant and theoretically sound methods for computation, estimation, and decision-making in structured, high-dimensional, dynamic environments, with applications to macroeconomics and causal inference.</description>
     </item>
 
     <item>

index.html

@@ -302,7 +302,7 @@ <h3 itemprop="worksFor" itemscope itemtype="http://schema.org/Organization">
 
 <h2 id="about">About</h2>
 
-<p>In my research I use insights from nonparametric and functional data analysis to devise new, rigorously guaranteed methods for solving dynamic economic models with infinite dimensional uncertainty and apply these methods to understand the dynamics of economic heterogeneity in a variety of contexts.</p>
+<p>In my research I combine approaches from Econometrics, Machine Learning, and High-dimensional Statistics to devise performant and theoretically sound methods for computation, estimation, and decision-making in structured, high-dimensional, dynamic environments, with applications to macroeconomics and causal inference.</p>
 
 
     <div class="row">
@@ -314,6 +314,8 @@ <h3>Interests</h3>
 
           <li>Econometrics</li>
 
+          <li>Machine Learning</li>
+
           <li>Macroeconomics</li>
 
           <li>Computational Economics</li>
@@ -381,6 +383,7 @@ <h1>Research</h1>
     David Childers, Jesús Fernández-Villaverde, Jesse Perla, Christopher Rackauckas, Peifan Wu</span>
   (2022).
   <a href="/publication/differentiablestatespace/" itemprop="name">Differentiable State Space Models and Hamiltonian Monte Carlo Estimation</a>.
+  Submitted.
 
   <p>
 
@@ -408,6 +411,10 @@ <h1>Research</h1>
 
 
 
+<a class="btn btn-primary btn-outline btn-xs" href="https://www.nber.org/papers/w30573" target="_blank" rel="noopener">
+  NBER WP30573
+</a>
+
 </p>
 </div>
 

publication/differentiablestatespace/index.html

@@ -17,7 +17,7 @@
 
 
 
-  <meta name="description" content="">
+  <meta name="description" content="We propose a methodology to take dynamic stochastic general equilibrium (DSGE) models to the data based on the combination of differentiable state-space models and the Hamiltonian Monte Carlo (HMC) sampler. First, we introduce a method for implicit automatic differentiation of perturbation solutions of DSGE models with respect to the model&#39;s parameters. We can use the resulting output for various tasks requiring gradients, such as building an HMC sampler, to estimate first- and second-order approximations of DSGE models. The availability of derivatives also enables a general filter-free method to estimate nonlinear, non-Gaussian DSGE models by sampling the joint likelihood of parameters and latent states. We show that the gradient-based joint likelihood sampling approach is superior in efficiency and robustness to standard Metropolis-Hastings samplers by estimating a canonical real business cycle model, a real small open economy model, and a medium-scale New Keynesian DSGE model.">
 
 
   <link rel="alternate" hreflang="en-us" href="/publication/differentiablestatespace/">
@@ -79,7 +79,7 @@
   <meta property="og:site_name" content="David Childers">
   <meta property="og:url" content="/publication/differentiablestatespace/">
   <meta property="og:title" content="Differentiable State Space Models and Hamiltonian Monte Carlo Estimation | David Childers">
-  <meta property="og:description" content="">
+  <meta property="og:description" content="We propose a methodology to take dynamic stochastic general equilibrium (DSGE) models to the data based on the combination of differentiable state-space models and the Hamiltonian Monte Carlo (HMC) sampler. First, we introduce a method for implicit automatic differentiation of perturbation solutions of DSGE models with respect to the model&#39;s parameters. We can use the resulting output for various tasks requiring gradients, such as building an HMC sampler, to estimate first- and second-order approximations of DSGE models. The availability of derivatives also enables a general filter-free method to estimate nonlinear, non-Gaussian DSGE models by sampling the joint likelihood of parameters and latent states. We show that the gradient-based joint likelihood sampling approach is superior in efficiency and robustness to standard Metropolis-Hastings samplers by estimating a canonical real business cycle model, a real small open economy model, and a medium-scale New Keynesian DSGE model.">
   <meta property="og:locale" content="en-us">
 
   <meta property="article:published_time" content="2022-10-06T00:00:00-04:00">
@@ -280,6 +280,9 @@ <h1 itemprop="name">Differentiable State Space Models and Hamiltonian Monte Carl
 
 
 
+    <h3>Abstract</h3>
+    <p class="pub-abstract" itemprop="text">We propose a methodology to take dynamic stochastic general equilibrium (DSGE) models to the data based on the combination of differentiable state-space models and the Hamiltonian Monte Carlo (HMC) sampler. First, we introduce a method for implicit automatic differentiation of perturbation solutions of DSGE models with respect to the model&rsquo;s parameters. We can use the resulting output for various tasks requiring gradients, such as building an HMC sampler, to estimate first- and second-order approximations of DSGE models. The availability of derivatives also enables a general filter-free method to estimate nonlinear, non-Gaussian DSGE models by sampling the joint likelihood of parameters and latent states. We show that the gradient-based joint likelihood sampling approach is superior in efficiency and robustness to standard Metropolis-Hastings samplers by estimating a canonical real business cycle model, a real small open economy model, and a medium-scale New Keynesian DSGE model.</p>
+
 
 
     <div class="row">
@@ -302,6 +305,18 @@ <h1 itemprop="name">Differentiable State Space Models and Hamiltonian Monte Carl
 
 
 
+    <div class="row">
+      <div class="col-sm-1"></div>
+      <div class="col-sm-10">
+        <div class="row">
+          <div class="col-xs-12 col-sm-3 pub-row-heading">Publication</div>
+          <div class="col-xs-12 col-sm-9">Submitted</div>
+        </div>
+      </div>
+      <div class="col-sm-1"></div>
+    </div>
+    <div class="visible-xs space-below"></div>
+
 
     <div class="row">
       <div class="col-sm-1"></div>
@@ -350,6 +365,10 @@ <h1 itemprop="name">Differentiable State Space Models and Hamiltonian Monte Carl
 
 
 
+<a class="btn btn-primary btn-outline" href="https://www.nber.org/papers/w30573" target="_blank" rel="noopener">
+  NBER WP30573
+</a>
+
 
 
           </div>

publication/index.html

@@ -303,6 +303,7 @@ <h1>Publications</h1>
   <span itemprop="author">
     David Childers, Jesús Fernández-Villaverde, Jesse Perla, Christopher Rackauckas, Peifan Wu</span>.
   <a href="/publication/differentiablestatespace/" itemprop="name">Differentiable State Space Models and Hamiltonian Monte Carlo Estimation</a>.
+  Submitted,
   2022.
   <p>
 
@@ -330,6 +331,10 @@ <h1>Publications</h1>
 
 
 
+<a class="btn btn-primary btn-outline btn-xs" href="https://www.nber.org/papers/w30573" target="_blank" rel="noopener">
+  NBER WP30573
+</a>
+
 </p>
 </div>