AI RESEARCH
Statistical Guarantees for Distributionally Robust Optimization with Optimal Transport and OT-Regularized Divergences
arXiv CS.LG
•
ArXi:2603.27871v1 Announce Type: cross We study finite-sample statistical performance guarantees for distributionally robust optimization (DRO) with optimal transport (OT) and OT-regularized divergence model neighborhoods. Specifically, we derive concentration inequalities for supervised learning via DRO-based adversarial