Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

0.3.2 #64

Merged
merged 4 commits into from
Jan 17, 2024
Merged

0.3.2 #64

merged 4 commits into from
Jan 17, 2024

Conversation

kristian-georgiev
Copy link
Member

Bug fixes and enhancements:

  • fix excessive CPU memory load from logging
  • remove unnecessary dependencies between featurizing & scoring methods
  • fix abstraction violation in projectors
  • bring back an example of iterative (as opposed to functional) gradient computer
  • add a ridge regularization option for the computation of the $(X^\top X)^{-1}$ term in the TRAK estimator.

JD-ETH and others added 4 commits January 5, 2024 10:10
…radients to device (#59)

* torch load gradients to device instead of CPU during finalize

loading data directly on device instead of moving from CPU to GPU in score computation steps

* Remove logging of raw tensors
finalize feature deletes the proj_matrix, but basic projector assumes it exists. remove dependency.
Co-authored-by: TheaperDeng <junweid2.illinois.edu>
* Updated score_computers.py for lambda_reg

* Updated traker.py to include a lambda_reg term in arguments

* minor fixes

---------

Co-authored-by: Kristian Georgiev <[email protected]>
@kristian-georgiev
Copy link
Member Author

Co-authors of commits: @TheaperDeng @JD-ETH @heale04

@kristian-georgiev kristian-georgiev merged commit 96a75b6 into main Jan 17, 2024
3 checks passed
@kristian-georgiev kristian-georgiev deleted the 0.3.2 branch January 17, 2024 19:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants