Work

Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond

Year: 2022

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2212.13669

Authors: Soma, Tasuku, Gatmiry, Khashayar, Gupta, Sharut, Jegelka, Stefanie

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4313305578

Cites:

Cited by: 1

Related to: 10