Distributionally Robust Stochastic Optimization with Wasserstein Distance

Abstract

Distributionally robust stochastic optimization (DRSO) is an approach to optimization under uncertainty in which, instead of assuming that there is a known true underlying probability distribution, one hedges against a chosen set of distributions. In this paper we first point out that the set of distributions should be chosen to be appropriate for the application at hand, and that some of the choices that have been popular until recently are, for many applications, not good choices. We next consider sets of distributions that are within a chosen Wasserstein distance from a nominal distribution. Such a choice of sets has two advantages: (1) The resulting distributions hedged against are more reasonable than those resulting from other popular choices of sets. (2) The problem of determining the worst-case expectation over the resulting set of distributions has desirable tractability properties. We derive a strong duality reformulation of the corresponding DRSO problem and construct approximate worst-case distributions explicitly via the first-order optimality conditions of the dual problem. Our contributions are four-fold. (i) We identify necessary and sufficient conditions for the existence of a worst-case distribution, which are naturally related to the growth rate of the objective function. (ii) We show that the worst-case distributions resulting from an appropriate Wasserstein distance have a concise structure and a clear interpretation. (iii) Using this structure, we show that data-driven DRSO problems can be approximated to any accuracy by robust optimization problems, and thereby many DRSO problems become tractable by using tools from robust optimization. (iv) Our strong duality result holds in a very general setting. As examples, we show that it can be applied to infinite-dimensional process control and intensity estimation for point processes.

Accepted by Mathematic of Operations Research

Cited by in corpus (14)

• Optimization under Uncertainty in the Era of Big Data and Deep Learning: When Machine Learning Meets Mathematical Programming
• Conic Programming Reformulations of Two-Stage Distributionally Robust Linear Programs over Wasserstein Balls
• Distributionally Robust Optimization: A Review
• Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
• Wasserstein Distributionally Robust Look-Ahead Economic Dispatch
• A dynamic game approach to distributionally robust safety specifications for stochastic systems
• Sample Out-Of-Sample Inference Based on Wasserstein Distance
• Sensitivity analysis of Wasserstein distributionally robust optimization problems
• Conic Reformulations for Kullback-Leibler Divergence Constrained Distributionally Robust Optimization and Applications
• Data-Driven Distributionally Robust Optimization for Long-Term Contract vs. Spot Allocation Decisions: Application to Electricity Markets
• Partition-based Distributionally Robust Optimization via Optimal Transport with Order Cone Constraints
• Model Calibration via Distributionally Robust Optimization: On the NASA Langley Uncertainty Quantification Challenge
• Data assimilation and online optimization with performance guarantees
• Optimization under Connected Uncertainty