Poster

Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees

Songkai Xue · Yuekai Sun · Mikhail Yurochkin

Hall J #718
[ Abstract ]
[ Paper [ Poster [ OpenReview
Tue 29 Nov 9 a.m. PST — 11 a.m. PST

Abstract:

We consider the task of training machine learning models with data-dependent constraints. Such constraints often arise as empirical versions of expected value constraints that enforce fairness or stability goals. We reformulate data-dependent constraints so that they are calibrated: enforcing the reformulated constraints guarantees that their expected value counterparts are satisfied with a user-prescribed probability. The resulting optimization problem is amendable to standard stochastic optimization algorithms, and we demonstrate the efficacy of our method on a fairness-sensitive classification task where we wish to guarantee the classifier's fairness (at test time).

Chat is not available.