Konsti trace regularization #104
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
- extend trace reg by its sepearate class
- grad, and norm regularization
- Norm regularizer - trace regularizer - grad variance regularizer
A schedule is a function that depends on the current epoch and rescales the regularization factor. This function can also be defined by the user.
Add more tests to regularizers
- process model instead of apply_fn - adapt and add tests - write example script for the regularizer
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Outdated suggestions cannot be applied.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.
Add regularization to the training of neural networks.
There are two regularizers available:
Each regularizer comes with the option of using a schedule, that scales the effect of the regularization.