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

CardsList

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

  1. Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spaces

    Dec 29, 2024Linglingzhi Zhu, Yunqin Zhu, Yao XieDistributionally Robust OptimizationWasserstein Distributionally Robust Optimization