J. Blanchet and A. Shapiro, “Statistical Limit Theorems in Distributionally Robust Optimization,” 2023 Winter Simulation Conference (WSC), San Antonio, TX, USA, 2023, pp. 31-45, doi: 10.1109/WSC60868.2023.10408421.
Abstract
The goal of this paper is to develop a methodology for the systematic analysis of asymptotic statistical properties of data-driven DRO formulations based on their corresponding non-DRO counterparts. We illustrate our approach in various settings, including both phi-divergence and Wasserstein uncertainty sets. Different types of asymptotic behaviors are obtained depending on the rate at which the uncertainty radius decreases to zero as a function of the sample size and the geometry of the uncertainty sets.
Authors
Jose Blanchet, Alexander Shapiro
Publication date
2023/12/10
Conference
2023 Winter Simulation Conference (WSC)
Pages
31-45
Publisher
IEEE
