Add sigma to SGHMC and SGNHT #90
Merged
Conversation
This file contains hidden or 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
KaelanDt
approved these changes
May 15, 2024
Contributor
KaelanDt
left a comment
KaelanDt
left a comment
There was a problem hiding this comment.
LGTM! Just curious, does the addition of sigma make the tests past more smoothly (ie lower tol)?
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Outdated suggestions cannot be applied.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.
Adds a sigma parameter for the momenta target distribution of SGHMC and SGNHT. This is needed to get an equivalence with SGD+momenta when setting
temperature=0as SGD+momenta has three tuning parameters (lr, momentum, dampening) assuming no weight decay.