Fix Yogi optimizer #288
Merged
Fix Yogi optimizer #288
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
hbq1
approved these changes
Jan 25, 2022
|
FYI We will only be able to merge this and other CLs after the ICML 2022 deadline (on this Friday). Sorry for the inconvenience! |
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Outdated suggestions cannot be applied.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.
When I was implementing #279, I noticed that the Yogi optimizer was incorrectly implemented. We should not take the square of
signed_sqin_update_moment, and the coefficient to updatevis also different from that in_update_moment.After the fix, I need to change the learning rate to pass the test.