Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization

Abstract

Fairness researchers in machine learning (ML) have coalesced around several fairness criteria which provide formal definitions of what it means for an ML model to be fair. However, these criteria have some serious limitations. We identify four key shortcomings of these formal fairness criteria, and aim to help to address them by extending performative prediction to include a distributionally robust objective.

From a submission to Responsible Decision Making in Dynamics Environments Workshop at ICML 2022