# Learning Non-Discriminatory Predictors

arXiv: https://arxiv.org/abs/1702.06081 · HTML: https://mlsanity.com/paper/1702.06081/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2017.

## Built on by (most cited first, 3 of 3)

- [Query lower bounds for log-concave sampling](https://mlsanity.com/paper/2304.02599/) (2023)
- [Holistic Survey of Privacy and Fairness in Machine Learning](https://mlsanity.com/paper/2307.15838/) (2023)
- [Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networks](https://mlsanity.com/paper/2202.05395/) (2022)

## Abstract (arXiv)

We consider learning a predictor which is non-discriminatory with respect to a "protected attribute" according to the notion of "equalized odds" proposed by Hardt et al. [2016]. We study the problem of learning such a non-discriminatory predictor from a finite training set, both statistically and computationally. We show that a post-hoc correction approach, as suggested by Hardt et al, can be highly suboptimal, present a nearly-optimal statistical procedure, argue that the associated computational problem is intractable, and suggest a second moment relaxation of the non-discrimination definition for which learning is tractable.