Statistical Guarantees for Fairness Aware Plug-In Algorithms
Machine Learning
2021-07-28 v1 Machine Learning
Abstract
A plug-in algorithm to estimate Bayes Optimal Classifiers for fairness-aware binary classification has been proposed in (Menon & Williamson, 2018). However, the statistical efficacy of their approach has not been established. We prove that the plug-in algorithm is statistically consistent. We also derive finite sample guarantees associated with learning the Bayes Optimal Classifiers via the plug-in algorithm. Finally, we propose a protocol that modifies the plug-in approach, so as to simultaneously guarantee fairness and differential privacy with respect to a binary feature deemed sensitive.
Cite
@article{arxiv.2107.12783,
title = {Statistical Guarantees for Fairness Aware Plug-In Algorithms},
author = {Drona Khurana and Srinivasan Ravichandran and Sparsh Jain and Narayanan Unny Edakunni},
journal= {arXiv preprint arXiv:2107.12783},
year = {2021}
}
Comments
This paper was accepted at the workshop on Socially Responsible Machine Learning, ICML 2021