Poster
Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
Andrew Cotter · Maya Gupta · Heinrich Jiang · Nati Srebro · Karthik Sridharan · Serena Wang · Blake Woodworth · Seungil You
Pacific Ballroom #203
Keywords: [ Convex Optimization ] [ Fairness ] [ Game Theory and Mechanism Design ] [ Non-convex Optimization ] [ Statistical Learning Theory ]
Classifiers can be trained with data-dependent constraints to satisfy fairness goals, reduce churn, achieve a targeted false positive rate, or other policy goals. We study the generalization performance for such constrained optimization problems, in terms of how well the constraints are satisfied at evaluation time, given that they are satisfied at training time. To improve generalization, we frame the problem as a two-player game where one player optimizes the model parameters on a training dataset, and the other player enforces the constraints on an independent validation dataset. We build on recent work in two-player constrained optimization to show that if one uses this two-dataset approach, then constraint generalization can be significantly improved. As we illustrate experimentally, this approach works not only in theory, but also in practice.
Live content is unavailable. Log in and register to view live content