Simple and near-optimal algorithms for hidden stratification and multi-group learning
Machine Learning
2024-06-18 v2 Machine Learning
Abstract
Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. This paper studies the structure of solutions to the multi-group learning problem, and provides simple and near-optimal algorithms for the learning problem.
Cite
@article{arxiv.2112.12181,
title = {Simple and near-optimal algorithms for hidden stratification and multi-group learning},
author = {Christopher Tosh and Daniel Hsu},
journal= {arXiv preprint arXiv:2112.12181},
year = {2024}
}