Universal Generalization Guarantees for Wasserstein Distributionally Robust Models

arXiv:2402.11981v1 Announce Type: cross
Abstract: Distributionally robust optimization has emerged as an attractive way to train robust machine learning models, capturing data uncertainty and distribution shifts. Recent statistical analyses have proved that robust models built from Wasserstein ambiguity sets have nice generalization guarantees, breaking the curse of dimensionality. However, these results are obtained in specific cases, at the cost of approximations, or under assumptions difficult to verify in practice. In contrast, we establish, in this article, exact generalization guarantees that …

abstract arxiv breaking data dimensionality distribution machine machine learning machine learning models math.oc nice optimization robust robust models statistical stat.ml the curse of dimensionality train type uncertainty