Dennis Wei, Rahul Nair, et al.
NeurIPS 2022
Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling group discrimination, limiting distortion in individual data samples, and preserving utility. Several theoretical properties are established, including conditions for convexity, a characterization of the impact of limited sample size on discrimination and utility guarantees, and a connection between discrimination and estimation. Two instances of the proposed optimization are applied to datasets, including one on real-world criminal recidivism. Results show that discrimination can be greatly reduced at a small cost in classification accuracy and with precise control of individual distortion.
Dennis Wei, Rahul Nair, et al.
NeurIPS 2022
Flavio Du Pin Calmon, Dennis Wei, et al.
NeurIPS 2017
Rahul Nair, Massimiliano Mattetti, et al.
IJCAI 2021
Dmitry Malioutov, Sanjeeb Dash, et al.
AISTATS 2023