A minimax framework for quantifying risk-fairness trade-off in regression

DOI10.1214/22-AOS2198arXiv2007.14265MaRDI QIDQ6346014FDOQ6346014

Authors: Evgenii Chzhen, Nicolas Schreuder 

Publication date: 28 July 2020

Abstract: We propose a theoretical framework for the problem of learning a real-valued function which meets fairness requirements. This framework is built upon the notion of $alpha$-relative (fairness) improvement of the regression function which we introduce using the theory of optimal transport. Setting $alpha=0$ corresponds to the regression problem under the Demographic Parity constraint, while $alpha=1$ corresponds to the classical regression problem without any constraints. For $alphain(0,1)$ the proposed framework allows to continuously interpolate between these two extreme cases and to study partially fair predictors. Within this framework we precisely quantify the cost in risk induced by the introduction of the fairness constraint. We put forward a statistical minimax setup and derive a general problem-dependent lower bound on the risk of any estimator satisfying $alpha$-relative improvement constraint. We illustrate our framework on a model of linear regression with Gaussian design and systematic group-dependent bias, deriving matching (up to absolute constants) upper and lower bounds on the minimax risk under the introduced constraint. We provide a general post-processing strategy which enjoys fairness, risk guarantees and can be applied on top of any black-box algorithm. Finally, we perform a simulation study of the linear model and numerical experiments of benchmark data, validating our theoretical contributions.

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Linear regression; mixed models (62J05) Optimal transportation (49Q22) Minimax procedures in statistical decision theory (62C20)

This page was built for publication: A minimax framework for quantifying risk-fairness trade-off in regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6346014)