Prevent unused NaNs from marking constraints as infeasible in pareto_frontier_evaluator #2431
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D56953680 |
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2431 +/- ##
=======================================
Coverage 95.30% 95.30%
=======================================
Files 494 494
Lines 47920 47938 +18
=======================================
+ Hits 45670 45688 +18
Misses 2250 2250 ☔ View full report in Codecov by Sentry. |
) Summary: This would previously filter out the observations with missing metrics with a warning, which could lead to issues in downstream usage. Returning the observations with NaN lets the downstream users deal with NaNs while keeping the expected return shapes. Reviewed By: mpolson64 Differential Revision: D56949439
…frontier_evaluator (facebook#2431) Summary: `get_outcome_constraint_transforms` evaluates the constraints by taking the product of tensor `A` with `Y` and comparing the outcome to `rhs` (uses einsum for this). The product of `0` and `nan` evaluates to `nan`, leading to the constraint being marked infeasible, even if that `nan` is from some unused metric. By setting unused elements to `0`, this diff prevents such issues. Reviewed By: mpolson64 Differential Revision: D56953680
saitcakmak
force-pushed
the
export-D56953680
branch
from
0bd0152 to
1637e0c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D56953680 |
|
This pull request has been merged in 6f04957. |
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.
Summary:
get_outcome_constraint_transformsevaluates the constraints by taking the product of tensorAwithYand comparing the outcome torhs(uses einsum for this). The product of0andnanevaluates tonan, leading to the constraint being marked infeasible, even if thatnanis from some unused metric. By setting unused elements to0, this diff prevents such issues.Differential Revision: D56953680