Sinkhorn Distributionally Robust Optimization
From MaRDI portal
Publication:6378483
arXiv2109.11926MaRDI QIDQ6378483
Author name not available (Why is that?)
Publication date: 24 September 2021
Abstract: We study distributionally robust optimization (DRO) with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. Compared with Wasserstein DRO, our proposed approach offers enhanced computational tractability for a broader class of loss functions, and the worst-case distribution exhibits greater plausibility in practical scenarios. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased gradient oracles. Remarkably, this algorithm achieves near-optimal sample complexity for both smooth and nonsmooth loss functions, nearly matching the sample complexity of the Empirical Risk Minimization counterpart. Finally, we provide numerical examples using synthetic and real data to demonstrate its superior performance.
Has companion code repository: https://github.com/WalterBabyRudin/SDRO_code
This page was built for publication: Sinkhorn Distributionally Robust Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6378483)
