This repository has been archived by the owner on Aug 18, 2023. It is now read-only.
QMHL #189
Merged
QMHL #189
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
Closed
|
what you describe could mean we over-flow somewhere, I think if things LG with a reasonable number of samples (<=1e6) then we can consider the PR WAI imo. However, we should open an issue to track down the specific cause post-release. I'll review the PR now |
farice
previously approved these changes
Feb 17, 2022
|
Added #190. Also, what does WAI mean? |
|
WAI = working as intended! |
farice
approved these changes
Feb 17, 2022
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Implements QMHL for the new QHBM structure.
Part of #140.
@farice one thing I couldn't resolve was the following: as I increase the number of samples at line 46 of
qmhl_loss_test.py, line 269 starts to fail; for example, going from 1e6 to 1e7 samples causes the relative error to go to 0.065, whereas the tolerance is 0.02; and for 1e8 samples, relative error goes to 0.75