Orthounimodal Distributionally Robust Optimization: Representation, Computation, and Multivariate Extreme Event Applications
Abstract
This paper studies a basic notion of distributional shape known as orthounimodality (OU) and its use in shape-constrained distributionally robust optimization (DRO). As a key motivation, we argue how such type of DRO is well suited to tackle multivariate extreme event estimation by giving statistically valid confidence bounds on target extremal probabilities. In particular, we explain how our approach can alleviate the bias–variance trade-off and other technical complications in conventional extreme value theory, while gaining interpretability and robustness compared with existing distributional shape notions used in the DRO literature. We characterize the extreme points of the OU distribution class in terms of what we call OU sets and build a corresponding Choquet representation, which subsequently allows us to reduce DRO under OU constraints into moment problems over infinite-dimensional random variables. We then develop, in the bivariate setting, a geometric approach to reduce such moment problems into finite dimension via a specially constructed variational problem designed to eliminate suboptimal solutions. Numerical results illustrate how our approach gives rise to valid and competitive confidence bounds for extremal probabilities.
Funding: This work was supported by the National Science Foundation [Grants CMMI-1834710 and IIS-1849280].
Supplemental Material: The online appendix is available at https://doi.org/10.1287/moor.2023.0143.

