Bayes-Optimal Classifiers under Group Fairness
Abstract
Machine learning algorithms are becoming integrated into more and more high-stakes decision-making processes, such as in social welfare issues. Due to the need of mitigating the potentially disparate impacts from algorithmic predictions, many approaches have been proposed in the emerging area of fair machine learning. However, the fundamental problem of characterizing Bayes-optimal classifiers under various group fairness constraints has only been investigated in some special cases. Based on the classical Neyman-Pearson argument (Neyman and Pearson, 1933; Shao, 2003) for optimal hypothesis testing, this paper provides a unified framework for deriving Bayes-optimal classifiers under group fairness. This enables us to propose a group-based thresholding method we call FairBayes, that can directly control disparity, and achieve an essentially optimal fairness-accuracy tradeoff. These advantages are supported by thorough experiments.
Cite
@article{arxiv.2202.09724,
title = {Bayes-Optimal Classifiers under Group Fairness},
author = {Xianli Zeng and Edgar Dobriban and Guang Cheng},
journal= {arXiv preprint arXiv:2202.09724},
year = {2024}
}
Comments
This technical report has been largely superseded by our later paper: "Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing'' (arXiv:2402.02817). Please cite that one instead of this technical report