Title: Projection to fairness in statistical learning
Authors: Thibaut Le Gouic - Institut Mathematiques de Marseille (France) [presenting]
Jean-Michel Loubes - University of Toulouse (France)
Philippe Rigollet - Massachusetts Institute of Technology (United States)
Abstract: In the context of regression, we consider the fundamental question of making an estimator fair while preserving its prediction accuracy as much as possible. To that end, we define its projection to fairness as its closest fair estimator in a sense that reflects prediction accuracy. Our methodology leverages tools from optimal transport to constructing efficiently the projection to fairness of any given estimator as a simple post-processing step. Moreover, our approach precisely quantifies the cost of fairness, measured in terms of prediction accuracy.