Simple and near-optimal algorithms for hidden stratification and multi-group learning
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:21633-21657, 2022.
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.