Wasserstein Distributionally Robust Optimization

Overview

Wasserstein distributionally robust optimization (WDRO) chooses decisions that perform well even under the worst-case data distribution within an optimal-transport neighborhood of observed data. Researchers use Wasserstein duality, convex and semidefinite reformulations, transport maps, and stochastic or iterative algorithms to make these problems tractable. Applications include robust classification and regression, clustering, portfolio decisions, control, and safety, with evaluation spanning corruption tests, out-of-sample risk, and finite-sample guarantees. A central challenge is balancing protection against distribution shift with computational cost and conservatism, especially when choosing the ambiguity radius or when the assumed transport geometry misses structural changes in the data.

Latest papers

31 papers2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Dec 29, 2024

Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spaces

We study distributionally robust optimization (DRO) for robust inference when the worst-case distribution is continuous, leading to significant computational challenges due to the infinite-dimensional nature of the optimization problem. Unlike traditional discrete DRO approaches, which often suffer from scalability issues, limited generalization, and costly worst-case inference, our framework exploits Brenier's theorem to characterize the least favorable distribution as the pushforward of a transport map from a continuous reference measure. This characterization motivates our study of the minimax problem in Wasserstein space. We propose an iterative algorithmic framework with multiple variants and establish global convergence guarantees under mild assumptions, deriving complexity bounds in terms of subgradient evaluations and inexact Jordan-Kinderlehrer-Otto updates. Numerical results with neural network-based transport maps demonstrate that the proposed method enables both stable training of robust classifiers and effective worst-case inference for classification tasks.