Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
Wasserstein distributionally robust estimators have emerged as powerful models for prediction and decision-making under uncertainty. These estimators provide attractive generalization guarantees: the robust objective obtained from the training distribution is an exact upper bound on the true risk with high probability. However, existing guarantees either suffer from the curse of dimensionality, are restricted to specific settings, or lead to spurious error terms. In this paper, we show that these generalization guarantees actually hold on general classes of models, do not suffer from the curse of dimensionality, and can even cover distribution shifts at testing. We also prove that these results carry over to the newly-introduced regularized versions of Wasserstein distributionally robust problems.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDecision Making Under UncertaintySimilar Papers 제목 키워드 기반
Universal generalization guarantees for Wasserstein distributionally robust models
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 generalizati…
Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization
Distributionally robust optimization offers a compelling framework for model fitting in machine learning, as it systematically accounts for data uncertainty. Focusing on Wasserstein distributionally robust optimization, …
Statistical Guarantees for Distributionally Robust Optimization with Optimal Transport and OT-Regularized Divergences
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 concentratio…
Adversarial RobustnessDistributionally Robust Skeleton Learning of Discrete Bayesian Networks
We consider the problem of learning the exact skeleton of general discrete Bayesian networks from potentially corrupted data. Building on distributionally robust optimization and a regression approach, we propose to opti…
Distributionally Robust Logistic Regression
This paper proposes a distributionally robust approach to logistic regression. We use the Wasserstein distance to construct a ball in the space of probability distributions centered at the uniform distribution on the tra…
regression