Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization
Machine Learning
2022-07-14 v1 Artificial Intelligence
Optimization and Control
Machine Learning
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.
Cite
@article{arxiv.2207.05777,
title = {Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization},
author = {Liam Peet-Pare and Nidhi Hegde and Alona Fyshe},
journal= {arXiv preprint arXiv:2207.05777},
year = {2022}
}
Comments
From a submission to Responsible Decision Making in Dynamics Environments Workshop at ICML 2022