Fix S-Learner's leakage #79
Merged
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
kklein
commented
Aug 10, 2024
| @@ -32,12 +32,12 @@ on ground truth CATEs: | |||
|
|
|||
| | S-learner | causalml_in_sample | causalml_oos | econml_in_sample | econml_oos | metalearners_in_sample | metalearners_oos | | |||
| | :------------------------------------------------------------ | -----------------: | -----------: | ---------------: | ---------: | ---------------------: | ---------------: | | |||
| | synthetic_data_continuous_outcome_binary_treatment_linear_te | 14.5706 | 14.6248 | 14.5706 | 14.6248 | 14.5729 | 14.6248 | | |||
| | synthetic_data_binary_outcome_binary_treatment_linear_te | 0.229101 | 0.228616 | nan | nan | 0.229231 | 0.2286 | | |||
| | twins_pandas | 0.314253 | 0.318554 | nan | nan | 0.371613 | 0.319028 | | |||
There was a problem hiding this comment.
Note that the benchmarks were actually quite indicative beforehand! We were doing quite a bit worse than causalml in the in-sample scenario before this change.
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #79 +/- ##
==========================================
- Coverage 94.43% 94.41% -0.02%
==========================================
Files 15 15
Lines 1779 1774 -5
==========================================
- Hits 1680 1675 -5
Misses 99 99 ☔ View full report in Codecov by Sentry. |
MatthiasLoefflerQC
approved these changes
Aug 10, 2024
ArseniyZvyagintsevQC
approved these changes
Aug 12, 2024
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Outdated suggestions cannot be applied.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.
This PR seeks to address @ArseniyZvyagintsevQC 's finding that the current implementation of the S-Learner's estimation of the conditional average outcomes is not quite kosher in the in-sample scenario.
Concretely, having observed$X_i, Y_i, W_i=k$ , we currently consider $i$ to be unseen when estimating $\mathbb{E}[Y_i|X_i,W_i=k']$ if $k' \neq k$ . Yet, the estimator has seen $Y_i$ , which may lead to some leakage.
Checklist
CHANGELOG.rstentry