New Perspectives on Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimization

Author name not available (Why is that?)

Publication date: 7 March 2023

Abstract: We study optimal transport-based distributionally robust optimization problems where a fictitious adversary, often envisioned as nature, can choose the distribution of the uncertain problem parameters by reshaping a prescribed reference distribution at a finite transportation cost. In this framework, we show that robustification is intimately related to various forms of variation and Lipschitz regularization even if the transportation cost function fails to be (some power of) a metric. We also derive conditions for the existence and the computability of a Nash equilibrium between the decision-maker and nature, and we demonstrate numerically that nature's Nash strategy can be viewed as a distribution that is supported on remarkably deceptive adversarial samples. Finally, we identify practically relevant classes of optimal transport-based distributionally robust optimization problems that can be addressed with efficient gradient descent algorithms even if the loss function or the transportation cost function are nonconvex (but not both at the same time).

Has companion code repository: https://github.com/sorooshafiee/regularization_with_ot

This page was built for publication: New Perspectives on Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6428689)