Timezone: »

 
Oral
Fair regression via plug-in estimator and recalibration with statistical guarantees
Evgenii Chzhen · Christophe Denis · Mohamed Hebiri · Luca Oneto · Massimiliano Pontil

Wed Dec 09 06:30 AM -- 06:45 AM (PST) @ Orals & Spotlights: Social/Adversarial Learning
in Orals & Spotlights Track 20: Social/Adversarial Learning »

We study the problem of learning an optimal regression function subject to a fairness constraint. It requires that, conditionally on the sensitive feature, the distribution of the function output remains the same. This constraint naturally extends the notion of demographic parity, often used in classification, to the regression setting. We tackle this problem by leveraging on a proxy-discretized version, for which we derive an explicit expression of the optimal fair predictor. This result naturally suggests a two stage approach, in which we first estimate the (unconstrained) regression function from a set of labeled data and then we recalibrate it with another set of unlabeled data. The recalibration step can be efficiently performed via a smooth optimization. We derive rates of convergence of the proposed estimator to the optimal fair predictor both in terms of the risk and fairness constraint. Finally, we present numerical experiments illustrating that the proposed method is often superior or competitive with state-of-the-art methods.

[ Paper ]

Author Information

Evgenii Chzhen (Université Paris-Saclay, INRIA)
Christophe Denis (Universite Gustave Eiffel)
Mohamed Hebiri (Université Gustave Eiffel)
Luca Oneto (University of Genoa)
Massimiliano Pontil (IIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors