Kush R. Varshney, Dennis Wei, et al.
JDIQ
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.
Kush R. Varshney, Dennis Wei, et al.
JDIQ
Dennis Wei, Tian Gao, et al.
NeurIPS 2020
Dmitriy Katz-Rogozhnikov, Dennis Wei, et al.
ICDMW 2015
Vijay Arya, Rachel Bellamy, et al.
JMLR