{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T11:14:10Z","timestamp":1783336450937,"version":"3.54.6"},"reference-count":47,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Management Science"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>Wasserstein distributionally robust optimization (DRO) has gained prominence in operations research and machine learning as a powerful method for achieving solutions with favorable out-of-sample performance. Two compelling explanations for its success are the generalization bounds derived from Wasserstein DRO and its equivalence to regularization schemes commonly used in machine learning. However, existing results on generalization bounds and regularization equivalence are largely limited to settings where the Wasserstein ball is of a specific type, and the decision criterion takes certain forms of expected functions. In this paper, we show that generalization bounds and regularization equivalence can be obtained in a significantly broader setting, where the Wasserstein ball is of a general type and the decision criterion accommodates any form, including general risk measures. This not only addresses important machine learning and operations management applications but also expands to general decision-theoretical frameworks previously unaddressed by Wasserstein DRO. Our results are strong in that the generalization bounds do not suffer from the curse of dimensionality and the equivalency to regularization is exact. As a by-product, we show that Wasserstein DRO coincides with the recent max-sliced Wasserstein DRO for any decision criterion under affine decision rules, resulting in both being efficiently solvable as convex programs via our general regularization results. These general assurances provide a strong foundation for expanding the application of Wasserstein DRO across diverse domains of data-driven decision problems.<\/jats:p>\n                  <jats:p>This paper was accepted by Chung Piaw Teo, optimization.<\/jats:p>\n                  <jats:p>Funding: This work was supported by the National Natural Science Foundation of China [Grants 12371476 and 71921001] and the Natural Sciences and Engineering Research Council of Canada [Grant RGPIN-2023-05829].<\/jats:p>\n                  <jats:p>Supplemental Material: The online appendix is available at https:\/\/doi.org\/10.1287\/mnsc.2023.03895 .<\/jats:p>","DOI":"10.1287\/mnsc.2023.03895","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T13:57:32Z","timestamp":1762264652000},"page":"6104-6119","source":"Crossref","is-referenced-by-count":3,"title":["On Generalization and Regularization via Wasserstein Distributionally Robust Optimization"],"prefix":"10.1287","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2268-5285","authenticated-orcid":false,"given":"Qinyu","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei, Anhui 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8508-0526","authenticated-orcid":false,"given":"Jonathan Yu-Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Telfer School of Management, University of Ottawa, Ottawa, Ontario K1N 6N5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3428-004X","authenticated-orcid":false,"given":"Tiantian","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei, Anhui 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"109","reference":[{"key":"B1","volume-title":"Learning from Data","author":"Abu-Mostafa YS","year":"2012"},{"key":"B2","doi-asserted-by":"crossref","unstructured":"Aolaritei L, Lanzetti N, Chen H, D\u00f6rfler F (2025) Distributional uncertainty propagation via optimal transport.\n                      IEEE Trans. Automatic Control\n                      70(9):6080\u20136095.","DOI":"10.1109\/TAC.2025.3567559"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1757"},{"key":"B4","unstructured":"Bartl D, Drapeau S, Obloj J, Wiesel J (2020) Robust uncertainty sensitivity analysis. Preprint, submitted June 22, https:\/\/arxiv.org\/abs\/2006.12022."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(75)90025-2"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2028"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4155"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1017\/jpr.2019.49"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asab026"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1090\/memo\/1259"},{"key":"B11","unstructured":"Breiman L (1996) Bias, variance, and arcing classifiers. Technical report 460, Statistics Department, University of California, Berkeley."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.0685"},{"issue":"1","key":"B13","first-page":"1","volume":"19","author":"Chen R","year":"2018","journal-title":"J. Machine Learn. Res."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1110.0950"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0531(87)90093-7"},{"key":"B16","unstructured":"Chu H, Lin M, Toh KC (2024) Wasserstein distributionally robust optimization and its tractable regularization formulations. Preprint, submitted February 6, https:\/\/arxiv.org\/abs\/2402.03942."},{"issue":"7","key":"B17","first-page":"779","volume":"28","author":"Drucker H","year":"1997","journal-title":"Adv. Neural Inform. Processing Systems"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"issue":"2","key":"B19","first-page":"116","volume":"67","author":"Fishburn PC","year":"1977","journal-title":"Amer. Econom. Rev."},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1515\/9783110463453","author":"F\u00f6llmer H","year":"2016","journal-title":"Stochastic Finance: An Introduction in Discrete Time"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-014-0583-7"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2326"},{"key":"B23","unstructured":"Gao R, Chen X, Kleywegt AJ (2017) Wasserstein distributionally robust optimization and variation regularization. Preprint, submitted December 17, https:\/\/arxiv.org\/abs\/1712.06050."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2383"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-016-2326-x"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1080\/14697680701458307"},{"key":"B27","first-page":"130","author":"Kuhn D","year":"2019","journal-title":"INFORMS TutORials in Operations Research"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011215321374"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.77"},{"key":"B30","unstructured":"Olea JLM, Rush C, Velez A, Wiesel J (2022) The out-of-sample prediction error of the square-root-LASSO and related estimators. Preprint, submitted November 14, https:\/\/arxiv.org\/abs\/2211.07608."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2681(82)90008-7"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(02)00271-6"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.sorms.2013.03.001"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1080.0313"},{"key":"B35","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf B, Bartlett P, Smola A, Williamson R (1998) Support vector regression with automatic accuracy control.\n                      Internat. Conf. Artificial Neural Networks\n                      (Springer London, London), 111\u2013116.","DOI":"10.1007\/978-1-4471-1599-1_12"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015565"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.2307\/1911053"},{"issue":"103","key":"B38","first-page":"1","volume":"20","author":"Shafieezadeh-Abadeh S","year":"2019","journal-title":"J. Machine Learn. Res."},{"key":"B39","unstructured":"Shafieezadeh-Abadeh S, Aolaritei L, D\u00f6rfler F, Kuhn D (2023) New perspectives on regularization and computation in optimal transport-based distributionally robust optimization. Preprint, submitted March 7, https:\/\/arxiv.org\/abs\/2303.03900."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"B41","doi-asserted-by":"crossref","unstructured":"Sim M, Zhao L, Zhou M (2021) Tractable robust supervised learning models. Preprint, submitted December 14, https:\/\/doi.org\/10.2139\/ssrn.3981205.","DOI":"10.2139\/ssrn.3981205"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018628609742"},{"key":"B43","first-page":"5334","volume":"31","author":"Volpi R","year":"2018","journal-title":"Adv. Neural Inform. Processing Systems"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1020"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2014.1323"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.2307\/1911158"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2023.4810"}],"container-title":["Management Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/mnsc.2023.03895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T10:15:18Z","timestamp":1783332918000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/mnsc.2023.03895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1287\/mnsc.2023.03895"],"URL":"https:\/\/doi.org\/10.1287\/mnsc.2023.03895","relation":{},"ISSN":["0025-1909","1526-5501"],"issn-type":[{"value":"0025-1909","type":"print"},{"value":"1526-5501","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}