Research

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing

ICML

Authors

Published on

10/17/2019

Categories

ICML Machine Learning

A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying to find a classifier that distinguishes between two ideal distributions when given two mismatched distributions that are biased. Using Chernoff information, a tool in information theory, we theoretically demonstrate that, contrary to popular belief, there always exist ideal distributions such that optimal fairness and accuracy (with respect to the ideal distributions) are achieved simultaneously: there is no trade-off. Moreover, the same classifier yields the lack of a trade-off with respect to ideal distributions while yielding a trade-off when accuracy is measured with respect to the given (possibly biased) dataset. To complement our main result, we formulate an optimization to find ideal distributions and derive fundamental limits to explain why a trade-off exists on the given biased dataset. We also derive conditions under which active data collection can alleviate the fairness-accuracy trade-off in the real world. Our results lead us to contend that it is problematic to measure accuracy with respect to data that reflects bias, and instead, we should be considering accuracy with respect to ideal, unbiased data.

This paper has been published at ICML 2020

Please cite our work using the BibTeX below.

@misc{dutta2020tradeoff,
      title={Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing}, 
      author={Sanghamitra Dutta and Dennis Wei and Hazar Yueksel and Pin-Yu Chen and Sijia Liu and Kush R. Varshney},
      year={2020},
      eprint={1910.07870},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}
Close Modal