From data to decisions: Distributionally robust optimization is optimal

Bart P.G. van Parys, P. Mohajerin Esfahani, Daniel Kuhn

Research output: Contribution to journalArticleScientificpeer-review

41 Citations (Scopus)
30 Downloads (Pure)

Abstract

We study stochastic programs where the decision maker cannot observe the distribution of the exogenous uncertainties but has access to a finite set of independent samples from this distribution. In this setting, the goal is to find a procedure that transforms the data to an estimate of the expected cost function under the unknown data-generating distribution, that is, a predictor, and an optimizer of the estimated cost function that serves as a near-optimal candidate decision, that is, a prescriptor. As functions of the data, predictors and prescriptors constitute statistical estimators. We propose a meta-optimization problem to find the least conservative predictors and prescriptors subject to constraints on their out-of-sample disappointment. The out-of-sample disappointment quantifies the probability that the actual expected cost of the candidate decision under the unknown true distribution exceeds its predicted cost. Leveraging tools from large deviations theory, we prove that this meta-optimization problem admits a unique solution: The best predictor-prescriptor-pair is obtained by solving a distributionally robust optimization problem over all distributions within a given relative entropy distance from the empirical distribution of the data.

Original languageEnglish
Pages (from-to)3387-3402
JournalManagement Science
Volume67
Issue number6
DOIs
Publication statusPublished - 2021

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Convex optimization
  • Data-driven optimization
  • Distributionally robust optimization
  • Large deviations theory
  • Relative entropy

Fingerprint

Dive into the research topics of 'From data to decisions: Distributionally robust optimization is optimal'. Together they form a unique fingerprint.

Cite this