Learning-Based Robust Optimization: Procedures and Statistical Guarantees
L. Jeff Hong, Zhiyuan Huang, Henry Lam
Management Science · 2021 · Volume 67 · Issue 6
Abstract
Robust optimization (RO) is a common approach to tractably obtain safeguarding solutions for optimization problems with uncertain constraints. In this paper, we study a statistical framework to integrate data into RO based on learning a prediction set using (combinations of) geometric shapes that are compatible with established RO tools and on a simple data-splitting validation step that achieves finite-sample nonparametric statistical guarantees on feasibility. We demonstrate how our required sample size to achieve feasibility at a given confidence level is independent of the dimensions of both the decision space and the probability space governing the stochasticity, and we discuss some approaches to improve the objective performances while maintaining these dimension-free statistical feasibility guarantees. This paper was accepted by Yinyu Ye, optimization.
Keywords
robust optimization, chance constraint, prediction set learning, quantile estimation
Enable JavaScript for citation tools and additional paper interactions.