MLP surrogate support #68
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mihajenko
reviewed
May 13, 2024
| self.fail(f'Import failed: {e}') | ||
|
|
||
| def test_initialization(self): | ||
| # Check if the NNClassifier is initialized correctly |
There was a problem hiding this comment.
Was incorrect initialization an issue?
There was a problem hiding this comment.
better safe than sorry
mihajenko
reviewed
May 13, 2024
| loss_grad_fn = jax.value_and_grad(self.forward_loss) | ||
| self.ncl = len(jnp.unique(X)) | ||
| X = jax.nn.one_hot(X, num_classes=self.ncl).reshape(X.shape[0], -1) | ||
| sample_batch = jnp.ones((1, X.shape[1])) |
There was a problem hiding this comment.
Did you test perf with other initializers? Not sure how well that behaves with a hardcoded PRNGKey.
There was a problem hiding this comment.
It shouldn't and it doesn't matter for a somewhat ok space of categorical problems we're considering here.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
To go beyond linear surrogates, mlp models are supported.