Sinkhorn Distributionally Robust Optimization

• 成果类型: Article; Early Access
• 署名作者: Wang, Tie; Gao, Rui; Xie, Yao
• 署名单位: The Chinese University of Hong Kong, Shenzhen; University of Texas System; University of Texas Austin; University System of Georgia; Georgia Institute of Technology
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.2023.0294
• 发表日期: 2025
• 关键词: Approximation; complexity; matrices; bounds

摘要

We study distributionally robust optimization with Sinkhorn distance: a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased subgradient estimators and derive its computational complexity guarantees. Finally, we provide numerical examples using synthetic and real data to demonstrate its superior performance.