Learning-based Robust Optimization: Procedures and Statistical Guarantees

arXiv1704.04342MaRDI QIDQ6285507FDOQ6285507

Authors: L. Jeff Hong, Zhi Yuan Huang, Henry Lam 

Publication date: 13 April 2017

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 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 discuss some approaches to improve the objective performances while maintaining these dimension-free statistical feasibility guarantees.

This page was built for publication: Learning-based Robust Optimization: Procedures and Statistical Guarantees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6285507)