Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond
This work addresses robustness and fairness issues in machine learning, but it appears incremental as it builds on existing DRO methods.
The paper tackles the problem of improving robustness and fairness in learning methods through distributionally robust optimization (DRO), achieving faster convergence rates and tight bounds for group DRO.
Distributionally robust optimization (DRO) can improve the robustness and fairness of learning methods. In this paper, we devise stochastic algorithms for a class of DRO problems including group DRO, subpopulation fairness, and empirical conditional value at risk (CVaR) optimization. Our new algorithms achieve faster convergence rates than existing algorithms for multiple DRO settings. We also provide a new information-theoretic lower bound that implies our bounds are tight for group DRO. Empirically, too, our algorithms outperform known methods.