{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T15:56:03Z","timestamp":1793289363431,"version":"4.5.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2021,4,20]],"date-time":"2021-04-20T00:00:00Z","timestamp":1618876800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,25]]},"abstract":"<jats:title>Summary<\/jats:title>\n               <jats:p>Estimators based on Wasserstein distributionally robust optimization are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a certain distance from the underlying empirical measure in a Wasserstein sense. While motivated by the need to identify optimal model parameters or decision choices that are robust to model misspecification, these distributionally robust estimators recover a wide range of regularized estimators, including square-root lasso and support vector machines, among others. This paper studies the asymptotic normality of these distributionally robust estimators as well as the properties of an optimal confidence region induced by the Wasserstein distributionally robust optimization formulation. In addition, key properties of min-max distributionally robust optimization problems are also studied; for example, we show that distributionally robust estimators regularize the loss based on its derivative, and we also derive general sufficient conditions which show the equivalence between the min-max distributionally robust optimization problem and the corresponding max-min formulation.<\/jats:p>","DOI":"10.1093\/biomet\/asab026","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T19:21:43Z","timestamp":1618600903000},"page":"295-315","source":"Crossref","is-referenced-by-count":29,"title":["Confidence regions in Wasserstein distributionally robust estimation"],"prefix":"10.1093","volume":"109","author":[{"given":"Jose","family":"Blanchet","sequence":"first","affiliation":[{"name":"Department of Management Science and Engineering, Stanford University, Huang Engineering Center, 475 Via Ortega, Stanford, California 94305, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karthyek","family":"Murthy","sequence":"additional","affiliation":[{"name":"Engineering Systems and Design pillar, Singapore University of Technology and Design, 8 Somapah Road, Singapore 487372"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nian","family":"Si","sequence":"additional","affiliation":[{"name":"Department of Management Science and Engineering, Stanford University, Huang Engineering Center, 475 Via Ortega, Stanford, California 94305, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,4,20]]},"reference":[{"key":"2022052609543766400_B1","volume-title":"Convergence of Probability Measures","author":"Billingsley,","year":"2013"},{"key":"2022052609543766400_B2","first-page":"97","article-title":"Distributionally robust groupwise regularization estimator","volume":"77","author":"Blanchet,","year":"2017","journal-title":"Proc. Mach. Learn. Res."},{"key":"2022052609543766400_B3","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1017\/jpr.2019.49","article-title":"Robust Wasserstein profile inference and applications to machine learning","volume":"56","author":"Blanchet,","year":"2019","journal-title":"J. Appl. Prob."},{"key":"2022052609543766400_B4","first-page":"3740","article-title":"Data-driven optimal transport cost selection for distributionally robust optimization","author":"Blanchet,","year":"2019","journal-title":"Proc. Winter Simulation Conf. (WSC)"},{"key":"2022052609543766400_B5","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1287\/moor.2018.0936","article-title":"Quantifying distributional model risk via optimal transport","volume":"44","author":"Blanchet,","year":"2019","journal-title":"Math. Oper. Res."},{"key":"2022052609543766400_B6","article-title":"Optimal transport based distributionally robust optimization: Structural properties and iterative schemes","author":"Blanchet,","year":"2020"},{"key":"2022052609543766400_B7","first-page":"517","article-title":"A robust learning approach for regression models based on distributionally robust optimization","volume":"19","author":"Chen,","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"2022052609543766400_B8","article-title":"Data-driven chance constrained programs over Wasserstein balls","author":"Chen,","year":"2018"},{"key":"2022052609543766400_B9","first-page":"756","article-title":"Distributionally robust formulation and model selection for the graphical lasso","volume":"108","author":"Cisneros-Velarde,","year":"2020","journal-title":"Proc. Mach. Learn. Res."},{"key":"2022052609543766400_B10","article-title":"Distributionally robust losses against mixture covariate shifts","author":"Duchi,","year":"2020"},{"key":"2022052609543766400_B11","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1214\/aos\/1176351052","article-title":"Asymptotic behavior of statistical estimators and of optimal solutions of stochastic optimization problems","volume":"16","author":"Dupacova,","year":"1988","journal-title":"Ann. Statist."},{"key":"2022052609543766400_B12","article-title":"Wasserstein distributional robustness and regularization in statistical learning","author":"Gao,","year":"2020"},{"key":"2022052609543766400_B13","article-title":"Distributionally robust stochastic optimization with Wasserstein distance","author":"Gao,","year":"2016"},{"key":"2022052609543766400_B14","first-page":"7913","article-title":"Robust hypothesis testing using Wasserstein uncertainty sets","author":"Gao,","year":"2018","journal-title":"Proc. 32nd Int. Conf. Neural Information Processing Systems"},{"key":"2022052609543766400_B15","article-title":"The behavior of maximum likelihood estimates under nonstandard conditions","volume-title":"Proc. 5th Berkeley Symp. Mathematical Statistics and Probability","author":"Huber,","year":"1967"},{"key":"2022052609543766400_B16","first-page":"1356","article-title":"Asymptotics for lasso-type estimators","volume":"28","author":"Knight,","year":"2000","journal-title":"Ann. Statist."},{"key":"2022052609543766400_B17","article-title":"Decomposition algorithm for distributionally robust optimization using Wasserstein metric","author":"Luo,","year":"2017"},{"key":"2022052609543766400_B18","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s10107-017-1172-1","article-title":"Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations","volume":"171","author":"Mohajerin Esfahani,","year":"2018","journal-title":"Math. Program."},{"key":"2022052609543766400_B19","volume-title":"Theory of Random Sets","author":"Molchanov,","year":"2005"},{"key":"2022052609543766400_B20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1093\/biomet\/75.2.237","article-title":"Empirical likelihood ratio confidence intervals for a single functional","volume":"75","author":"Owen,","year":"1988","journal-title":"Biometrika"},{"key":"2022052609543766400_B21","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1214\/aos\/1176347494","article-title":"Empirical likelihood ratio confidence regions","volume":"18","author":"Owen,","year":"1990","journal-title":"Ann. Statist."},{"key":"2022052609543766400_B22","volume-title":"Empirical Likelihood","author":"Owen,","year":"2001"},{"key":"2022052609543766400_B23","first-page":"1576","article-title":"Distributionally robust logistic regression","author":"Shafieezadeh-Abadeh,","year":"2015","journal-title":"Proc. 28th Conf. Advances in Neural Information Processing Systems"},{"key":"2022052609543766400_B24","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1214\/aos\/1176347146","article-title":"Asymptotic properties of statistical estimators in stochastic programming","volume":"17","author":"Shapiro,","year":"1989","journal-title":"Ann. Statist."},{"key":"2022052609543766400_B25","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/BF02204815","article-title":"Asymptotic analysis of stochastic programs","volume":"30","author":"Shapiro,","year":"1991","journal-title":"Ann. Oper. Res."},{"key":"2022052609543766400_B26","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1287\/moor.18.4.829","article-title":"Asymptotic behavior of optimal solutions in stochastic programming","volume":"18","author":"Shapiro,","year":"1993","journal-title":"Math. Oper. Res."},{"key":"2022052609543766400_B27","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1214\/aos\/1015952006","article-title":"On the asymptotics of constrained local $m$-estimators","volume":"28","author":"Shapiro,","year":"2000","journal-title":"Ann. Statist."},{"key":"2022052609543766400_B28","article-title":"Certifiable distributional robustness with principled adversarial training","author":"Sinha,","year":"2018","journal-title":"Proc. Int. Conf. Learning Representations"},{"key":"2022052609543766400_B29","article-title":"Distributionally robust deep learning as a generalization of adversarial training","author":"Staib,","year":"2017","journal-title":"Proc. NIPS Workshop on Machine Learning and Computer Security"},{"key":"2022052609543766400_B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2545-2","volume-title":"Weak Convergence and Empirical Processes: With Applications to Statistics","author":"van der Vaart,","year":"1996"},{"key":"2022052609543766400_B31","first-page":"5339","article-title":"Generalizing to unseen domains via adversarial data augmentation","author":"Volpi,","year":"2018","journal-title":"Proc. 32nd Int. Conf. Neural Information Processing Systems"},{"key":"2022052609543766400_B32","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/LCSYS.2017.2711553","article-title":"A convex optimization approach to distributionally robust Markov decision processes with Wasserstein distance","volume":"1","author":"Yang,","year":"2017","journal-title":"IEEE Control Syst. Lett."},{"key":"2022052609543766400_B33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3030884","article-title":"Wasserstein distributionally robust stochastic control: A data-driven approach","author":"Yang,","year":"2020","journal-title":"IEEE Trans. Automatic Control"},{"key":"2022052609543766400_B34","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.orl.2018.01.011","article-title":"Data-driven risk-averse stochastic optimization with Wasserstein metric","volume":"46","author":"Zhao,","year":"2018","journal-title":"Oper. Res. Lett."}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asab026\/42620396\/asab026.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/109\/2\/295\/43832477\/asab026.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/109\/2\/295\/43832477\/asab026.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T09:58:33Z","timestamp":1653559113000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/109\/2\/295\/6239705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,20]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,4,20]]},"published-print":{"date-parts":[[2022,5,25]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asab026","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,6,1]]},"published":{"date-parts":[[2021,4,20]]}}}