Repository navigation
Conversation
Summary: # Why LCBench constructs its numeric feature columns with a set difference. Process hash randomization can therefore change the feature order passed to the random forest, changing benchmark predictions even with the same random seed. # Changes - Preserve the declared parameter order when selecting non-logarithmic columns for both the metric and runtime surrogates. - Assert the exact numeric and logarithmic feature lists passed to both surrogate constructors. This establishes a deterministic order for new surrogate fits. Predictions can differ from historical fits that used another feature permutation; existing benchmark calibration constants and historical results are not recalculated. # Examples The numeric features are always `max_dropout`, `num_layers`, `weight_decay`, in that order, instead of a process-dependent permutation. Differential Revision: D130805946
meta-cla
Bot
added
the
CLA Signed
|
@ltiao has exported this pull request. If you are a Meta employee, you can view the originating Diff in D130805946. |
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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:
Why
LCBench constructs its numeric feature columns with a set difference. Process hash randomization can therefore change the feature order passed to the random forest, changing benchmark predictions even with the same random seed.
Changes
This establishes a deterministic order for new surrogate fits. Predictions can differ from historical fits that used another feature permutation; existing benchmark calibration constants and historical results are not recalculated.
Examples
The numeric features are always
max_dropout,num_layers,weight_decay, in that order, instead of a process-dependent permutation.Differential Revision: D130805946