EUVIMEDEUVIMED entdecken
Crossref

Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality

Rui Gao

Operations Research · 2023-11 · 71 (6) · 2291-2306

DOI: 10.1287/opre.2022.2326 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Operations Research, 2023-11. Verfasst von Rui Gao. Die Arbeit wurde bisher 69-mal zitiert (Crossref) und nennt 72 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wasserstein distributionally robust optimization is a recent emerging modeling paradigm for decision making under data uncertainty. Because of its computational tractability and interpretability, it has achieved great empirical successes across several application domains in operations research, computer science, engineering, and business analytics. Despite its recent empirical success, existing performance guarantees for generic problems are not yet satisfactory. In this paper, we develop the first finite-sample guarantee without suffering from the curse of dimensionality, which describes how the out-of-sample performance of a robust solution depends on the sample size, dimension of the uncertainty, and the complexity of the loss function class in a nearly optimal way.

Zitieren

APA

Gao, R. (2023). Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality. Operations Research, 71(6), 2291-2306. https://doi.org/10.1287/opre.2022.2326

Vancouver

Gao R. Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality. Operations Research. 2023;71(6):2291-2306. doi:10.1287/opre.2022.2326

BibTeX
@article{Gao2023,
  author = {Gao, Rui},
  title = {Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality},
  journal = {Operations Research},
  year = {2023},
  volume = {71},
  number = {6},
  pages = {2291--2306},
  doi = {10.1287/opre.2022.2326}
}
Kostenlos starten →