Doulitsa Press Release Submission

News that change your days

Multicalibrated Regression for Downstream Fairness. (arXiv:2209.07312v1 [cs.LG])

[Submitted on 15 Sep 2022] Download PDF Abstract: We show how to take a regression function $hat{f}$ that is appropriately ``multicalibrated'' and efficiently post-process it into an approximately error minimizing classifier satisfying a large variety of fairness constraints. The post-processing requires no labeled data, and only a modest amount of unlabeled data and computation. The…

[Submitted on 15 Sep 2022]

Download PDF

Abstract: We show how to take a regression function $hat{f}$ that is appropriately
“multicalibrated” and efficiently post-process it into an approximately error
minimizing classifier satisfying a large variety of fairness constraints. The
post-processing requires no labeled data, and only a modest amount of unlabeled
data and computation. The computational and sample complexity requirements of
computing $hat f$ are comparable to the requirements for solving a single fair
learning task optimally, but it can in fact be used to solve many different
downstream fairness-constrained learning problems efficiently. Our
post-processing method easily handles intersecting groups, generalizing prior
work on post-processing regression functions to satisfy fairness constraints
that only applied to disjoint groups. Our work extends recent work showing that
multicalibrated regression functions are “omnipredictors” (i.e. can be
post-processed to optimally solve unconstrained ERM problems) to constrained
optimization.

Submission history

From: Aaron Roth [view email]


[v1]
Thu, 15 Sep 2022 14:16:01 UTC (1,839 KB)

About Post Author

WP2Social Auto Publish Powered By : XYZScripts.com