Optimal algorithms for group distributionally robust optimization and beyond
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
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 up to a log factor for group DRO. Empirically, too, our algorithms outperform known methods.
BibTeX
@misc{soma2024optimal,
author = {Tasuku Soma and Khashayar Gatmiry and Sharut Gupta and Stefanie Jegelka},
title = {{Optimal algorithms for group distributionally robust optimization and beyond}},
year = {2024},
url = {https://openreview.net/forum?id=IQDSUpp69I},
howpublished = {OpenReview},
note = {Submitted to ICLR 2024},
}