Chzhen, E; Denis, C; Hebiri, M; Oneto, L; Pontil, M; (2020) Fair regression with wasserstein barycenters. In: Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020). (pp. pp. 1-11).

Preview

PDF fair-regression-with-wasserstein-barycenters-Paper.pdf - Published Version Download (617kB) | Preview

Abstract

We study the problem of learning a real-valued function that satisfies the Demographic Parity constraint. It demands the distribution of the predicted output to be independent of the sensitive attribute. We consider the case that the sensitive attribute is available for prediction. We establish a connection between fair regression and optimal transport theory, based on which we derive a close form expression for the optimal fair predictor. Specifically, we show that the distribution of this optimum is the Wasserstein barycenter of the distributions induced by the standard regression function on the sensitive groups. This result offers an intuitive interpretation of the optimal fair prediction and suggests a simple post-processing algorithm to achieve fairness. We establish risk and distribution-free fairness guarantees for this procedure. Numerical experiments indicate that our method is very effective in learning fair models, with a relative increase in error rate that is inferior to the relative gain in fairness.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item