Distributionally Robust Optimization over Incomparable Spaces
Abstract
Distributionally robust optimization (DRO) provides a principled framework for making decisions under uncertainty when the underlying distribution may be incorrectly specified. A widely used approach builds on ideas from optimal transport (OT) as a means of measuring differences between distributions. However, this depends on these distributions residing in the same space. In certain settings, the reference data distribution we have and the space on which we make our decision may be different, which renders classical OT techniques impossible. In this paper, we provide a new DRO formulation in which ambiguity sets are defined through the Gromov-Wasserstein distance, which is an extension of OT to pairs of distributions residing in incomparable spaces. We show that several seemingly unrelated optimization formulations, including conditional value-at-risk minimization, group distributionally robust optimization, robust graph k-median, and k-median with outliers, can be recovered as special cases of our formulation. We describe the computational aspects of solving the proposed formulation based on the doubly-nonnegative relaxation. Last, we illustrate the framework through experiments on clustering over incomparable spaces and stochastic graph k-median.
Related
- Group Distributionally Robust Optimization over Decentralized Networks
- On Survival Time in Robust Optimization over Time for Discrete Search Spaces
- Data-driven joint optimization of maintenance and spare parts provisioning: A distributionally robust approach
- Conformal-DRO: Distributionally Robust Optimization with Conformalized Ambiguity Set
- Calibrating Ambiguity Set via Diagnostic Transport for Distributionally Robust Optimization
BibTeX
@misc{chen2026distributionally,
title = {{Distributionally Robust Optimization over Incomparable Spaces}},
author = {Junyu Chen and Jieling Shi and Yong Sheng Soh},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01557},
eprint = {2611.01557},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01557},
}
RIS
TY - UNPB
TI - Distributionally Robust Optimization over Incomparable Spaces
AU - Junyu Chen
AU - Jieling Shi
AU - Yong Sheng Soh
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01557
UR - https://arxiv.org/abs/2611.01557
AB - Distributionally robust optimization (DRO) provides a principled framework for making decisions under uncertainty when the underlying distribution may be incorrectly specified. A widely used approach builds on ideas from optimal transport (OT) as a means of measuring differences between distributions. However, this depends on these distributions residing in the same space. In certain settings, the reference data distribution we have and the space on which we make our decision may be different, which renders classical OT techniques impossible. In this paper, we provide a new DRO formulation in which ambiguity sets are defined through the Gromov-Wasserstein distance, which is an extension of OT to pairs of distributions residing in incomparable spaces. We show that several seemingly unrelated optimization formulations, including conditional value-at-risk minimization, group distributionally robust optimization, robust graph k-median, and k-median with outliers, can be recovered as special cases of our formulation. We describe the computational aspects of solving the proposed formulation based on the doubly-nonnegative relaxation. Last, we illustrate the framework through experiments on clustering over incomparable spaces and stochastic graph k-median.
ER -