Feature/mfkans #201
Open
Feature/mfkans #201
+1,253
−151
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
RBirmiwal
approved these changes
Oct 22, 2024
|
@drgona @RBirmiwal please take a look and let me know if this looks good! If yes, we are good to merge. Thank you! p.s.: the main thing to review here is the p3 KAN notebook. |
drgona
requested changes
Jan 10, 2025
| @@ -250,6 +252,11 @@ def train(self): | |||
| alpha_loss = node.callable.get_alpha_loss() | |||
| output[self.train_metric] += alpha_loss | |||
|
|
|||
| for node in self.model.nodes: | |||
There was a problem hiding this comment.
What is the motivation to modify the trainer itself to include this KAN regularization loss?
This does not seem very modular solution. We can simply instantiate the regularization loss as a separate loss term during problem formulation rather than handling it internally via trainer.
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Outdated suggestions cannot be applied.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.
Adding example of multi-fidelity KANs