Supervised Learning without Discrimination

As machine learning is increasingly being used in areas protected by anti discrimination law, or in other domains which are socially and morally sensitive, the problem of algorithmically measuring and avoiding prohibited discrimination in machine learning is pressing. What does it mean for a predictor to not discriminate with respect to protected group (e.g. according to race, gender, etc)? We propose a notion of non-discrimination that can be measured statistically, used algorithmically, and avoids many of the pitfalls of previous definitions. We further study what type of discrimination and non-discrimination can be identified with oblivious tests, which treat the predictor as an opaque black-box, and what different oblivious tests tell us about possible discrimination. Joint work with Suriya Gunasekar, Mortiz Hardt, Mesrob Ohannessian, Eric Pierce and Blake Woodwoorth.