Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality
From MaRDI portal
Abstract: Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable solutions by hedging against data perturbations in Wasserstein distance. Despite its recent empirical success in operations research and machine learning, existing performance guarantees for generic loss functions are either overly conservative due to the curse of dimensionality, or plausible only in large sample asymptotics. In this paper, we develop a non-asymptotic framework for analyzing the out-of-sample performance for Wasserstein robust learning and the generalization bound for its related Lipschitz and gradient regularization problems. To the best of our knowledge, this gives the first finite-sample guarantee for generic Wasserstein DRO problems without suffering from the curse of dimensionality. Our results highlight that Wasserstein DRO, with a properly chosen radius, balances between the empirical mean of the loss and the variation of the loss, measured by the Lipschitz norm or the gradient norm of the loss. Our analysis is based on two novel methodological developments that are of independent interest: 1) a new concentration inequality controlling the decay rate of large deviation probabilities by the variation of the loss and, 2) a localized Rademacher complexity theory based on the variation of the loss.
Recommendations
- Wasserstein distributionally robust optimization and variation regularization
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- Regularization for Wasserstein distributionally robust optimization
- Decomposition algorithm for distributionally robust optimization using Wasserstein metric with an application to a class of regression models
- Distributionally Robust Stochastic Optimization with Wasserstein Distance
Cited in
(12)- Distributionally Robust Losses for Latent Covariate Mixtures
- Wasserstein distributionally robust optimization and variation regularization
- Residuals-based distributionally robust optimization with covariate information
- Distributionally robust optimization with generalized total variation ambiguity sets
- Outlier-robust nonsmooth stochastic optimization
- Wasserstein distributionally robust optimization and its tractable regularization formulation
- Guaranteed bounds for optimal stopping problems using kernel-based non-asymptotic uniform confidence bands
- Distributionally robust optimization and robust statistics
- Nonlinear distributionally robust optimization
- Distributionally robust optimization
- Robustness assessment of climate policies towards carbon neutrality: a DRO-IAMS approach
- First-order conditions for optimization in the Wasserstein space
This page was built for publication: Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6196762)
