Equality of Opportunity in Supervised Learning
Abstract
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy.
Cite
Text
Hardt et al. "Equality of Opportunity in Supervised Learning." Neural Information Processing Systems, 2016.Markdown
[Hardt et al. "Equality of Opportunity in Supervised Learning." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/hardt2016neurips-equality/)BibTeX
@inproceedings{hardt2016neurips-equality,
title = {{Equality of Opportunity in Supervised Learning}},
author = {Hardt, Moritz and Price, Eric and Ecprice, and Srebro, Nati},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {3315-3323},
url = {https://mlanthology.org/neurips/2016/hardt2016neurips-equality/}
}