2022 review

DISTRIBUTIONALLY ROBUST OPTIMIZATION: A REVIEW ON THEORY AND APPLICATIONS

[Review of ]. NUMERICAL ALGEBRA CONTROL AND OPTIMIZATION, 12(1), 159–212.

By: F. Lin*, X. Fang* & Z. Gao

author keywords: Distributionally robust optimization; uncertain decision-making; tractable methods; machine learning; operations research
TL;DR: This paper starts with reviewing the modeling power and computational attractiveness of DRO approaches, induced by the ambiguity sets structure and tractable robust counterpart reformulations, and summarizes the efficient solution methods, out-of-sample performance guarantee, and convergence analysis. (via Semantic Scholar)
Source: Web Of Science
Added: November 29, 2021

<p style='text-indent:20px;'>In this paper, we survey the primary research on the theory and applications of distributionally robust optimization (DRO). We start with reviewing the modeling power and computational attractiveness of DRO approaches, induced by the ambiguity sets structure and tractable robust counterpart reformulations. Next, we summarize the efficient solution methods, out-of-sample performance guarantee, and convergence analysis. Then, we illustrate some applications of DRO in machine learning and operations research, and finally, we discuss the future research directions.</p>