REVIEW 2 cited by
Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Group Distributionally Robust Optimization with Flexible Sample Queries
A flexible-sampling GDRO algorithm achieves O(1/t sqrt(sum_j m/r_j log m)) high-probability optimization error, generalizing prior r=1 and r=m guarantees.
-
Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty
A min-max-sup extension of Group DRO that adds a Wasserstein ball around each group's empirical distribution, with a descent-mirror-ascent algorithm and Adult income experiments.
Discussion (0). Continue with ORCID to comment.