{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:11:42Z","timestamp":1779905502905,"version":"3.53.1"},"reference-count":118,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Operations Research"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:p>Entropy-Regularized Wasserstein Distributionally Robust Optimization<\/jats:p>\n                  <jats:p>Uncertainty in data poses a central challenge in operations research. Distributionally robust optimization (DRO) offers a principled framework for addressing this challenge by producing solutions resilient to distributional variations. Among various DRO approaches, the Wasserstein DRO has received significant attention though its computational efficiency relies on stringent assumptions, and its worst case distributions are typically discrete. In \u201cSinkhorn Distributionally Robust Optimization,\u201d Wang, Gao, and Xie leverage the Sinkhorn distance\u2014an entropy-regularized variant of the Wasserstein distance\u2014to more realistically model uncertainty, enhancing computational efficiency. The authors establish a strong duality reformulation and propose a first order stochastic mirror descent algorithm with provable complexity guarantees for general loss functions. Unlike Wasserstein DRO, Sinkhorn DRO yields continuous worst case distributions, offering a more flexible representation of practical uncertainties. Extensive experiments in the newsvendor problem, portfolio optimization, and adversarial classification demonstrate its superior performance in both out-of-sample performance and efficiency.<\/jats:p>","DOI":"10.1287\/opre.2023.0294","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T18:44:54Z","timestamp":1760553894000},"page":"1581-1603","source":"Crossref","is-referenced-by-count":3,"title":["Sinkhorn Distributionally Robust Optimization"],"prefix":"10.1287","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8623-4622","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0145-8577","authenticated-orcid":false,"given":"Rui","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Information, Risk, and Operations Management, University of Texas at Austin, Austin, Texas 78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6777-2951","authenticated-orcid":false,"given":"Yao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1110.1011"},{"key":"B2","first-page":"1","volume":"30","author":"Altschuler J","year":"2017","journal-title":"Adv. Neural Inform. Processing Systems"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-69033-9"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2023019"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.2307\/2525582"},{"key":"B6","doi-asserted-by":"crossref","unstructured":"Bai Y, Wu X, Ozgur A (2020) Information constrained optimal transport: From Talagrand, to Marton, to Cover.\n                      2020 IEEE Internat. Sympos. Inform. Theory\n                      (IEEE Press, Piscataway, NJ), 2210\u20132215.","DOI":"10.1109\/ISIT44484.2020.9174478"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2015.0134"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3253"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0710-z"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2017.2952"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704259"},{"key":"B13","doi-asserted-by":"crossref","unstructured":"Blanchet J, Glynn PW (2015) Unbiased Monte Carlo for optimization and functions of expectations via multi-level randomization.\n                      2015 Winter Simulation Conf.\n                      (IEEE, Piscataway, NJ), 3656\u20133667.","DOI":"10.1109\/WSC.2015.7408524"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/9781119721871.ch1"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2018.0936"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4155"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1017\/jpr.2019.49"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2021.0233"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asab026"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1178"},{"key":"B21","first-page":"1","volume":"32","author":"Blanchet J","year":"2019","journal-title":"Wallach H, Larochelle H, Beygelzimer A, d'Alch\u00e9-Buc F, Fox E, Garnett R, eds. Adv. Neural Inform. Processing Systems"},{"key":"B22","author":"Chen R","year":"2019","journal-title":"Wallach H, Larochelle H, Beygelzimer A, d'Alch\u00e9-Buc F, Fox E, Garnett R, eds. Adv. Neural Inform. Processing Systems, vol. 32 (Curran Associates, Inc., Red Hook, NY), 1\u201311."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-020-00234-7"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2330"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1799"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2955031"},{"key":"B27","first-page":"215","volume":"77","author":"Coates A","year":"2011","journal-title":"Gordon G, Dunson D, Dud\u00edk M, eds. Proc. 14th Internat. Conf. Artificial Intelligence Statist."},{"key":"B28","doi-asserted-by":"crossref","unstructured":"Cohen MB, Lee YT, Miller G, Pachocki J, Sidford A (2016) Geometric median in nearly linear time.\n                      Proc. 48th Annual ACM Sympos. Theory Comput.\n                      (Association for Computing Machinery, New York), 9\u201321.","DOI":"10.1145\/2897518.2897647"},{"key":"B29","doi-asserted-by":"crossref","unstructured":"Courty N, Flamary R, Tuia D (2014) Domain adaptation with regularized optimal transport. Calders T, Esposito F, H\u00fcllermeier E, Meo R, eds.\n                      Joint Eur. Conf. Machine Learn. Knowledge Discovery Databases, ECML PKDD 2014\n                      , Lecture Notes in Computer Science, vol. 8724 (Springer, Berlin), 274\u2013289.","DOI":"10.1007\/978-3-662-44848-9_18"},{"key":"B30","author":"Courty N","year":"2017","journal-title":"Adv. Neural Inform. Processing Systems, vol. 30 (Curran Associates, Inc., Red Hook, NY), 1\u201310."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"B32","volume-title":"Elements of Information Theory","author":"Cover TM","year":"2006"},{"key":"B33","first-page":"2292","volume":"26","author":"Cuturi M","year":"2013","journal-title":"Adv. Neural Inform. Processing Systems"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0741"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177731829"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1110.1005"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2020.1085"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12280"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"B40","doi-asserted-by":"crossref","unstructured":"Feng Y, Schl\u00f6gl E (2018) Model risk measurement under Wasserstein distance. Preprint, submitted September 11, https:\/\/arxiv.org\/abs\/1809.03641.","DOI":"10.2139\/ssrn.3248825"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.2307\/1401846"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2326"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2383"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2383"},{"key":"B45","unstructured":"Genevay A, Peyre G, Cuturi M (2018) Learning generative models with Sinkhorn divergences. Storkey A, Perez-Cruz F, eds.\n                      Proc. 21st Internat. Conf. Artificial Intelligence Statist.\n                      , vol. 84 (PMLR, New York), 1608\u20131617."},{"key":"B46","volume":"29","author":"Genevay A","year":"2016","journal-title":"Adv. Neural Inform. Processing Systems"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0795"},{"key":"B48","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. Preprint, submitted December 20, https:\/\/arxiv.org\/abs\/1412.6572."},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1017\/CCOL0521382483"},{"key":"B50","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition.\n                      Proc. IEEE Conf. Comput. Vision Pattern Recognition\n                      (IEEE, Piscataway, NJ), 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"B51","first-page":"15","author":"He W","year":"2017","journal-title":"WOOT'17 Proc. 11th USENIX Conf. Offensive Technologies"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1137\/19M1284865"},{"key":"B53","author":"Hu Y","year":"2021","journal-title":"Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Vaughan JW, eds. Adv. Neural Inform. Processing Systems, vol. 34 (Curran Associates, Inc., Red Hook, NY), 1\u201313."},{"key":"B54","first-page":"1","volume":"33","author":"Hu Y","year":"2020","journal-title":"Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Adv. Neural Inform. Processing Systems"},{"key":"B55","unstructured":"Hu Z, Hong LJ (2012) Kullback-Leibler divergence constrained distributionally robust optimization.\n                      Optimization Online\n                      (November 23), https:\/\/optimization-online.org\/2012\/11\/3677\/."},{"key":"B56","unstructured":"Huang M, Ma S, Lai L (2021) A Riemannian block coordinate descent method for computing the projection robust Wasserstein distance. Meila M, Zhang T, eds.\n                      Proc. 38th Internat. Conf. Machine Learn.\n                      , vol. 139 (PMLR, New York), 4446\u20134455."},{"key":"B57","volume-title":"Foundations of Modern Probability","volume":"2","author":"Kallenberg O","year":"1997"},{"key":"B58","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. https:\/\/www.cs.utoronto.ca\/~kriz\/learning-features-2009-TR.pdf."},{"key":"B59","first-page":"15","volume":"52","author":"Kruithof J","year":"1937","journal-title":"De Ingenieur"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492924000084"},{"key":"B61","unstructured":"Le Y, Yang XS (2014) TinyImageNet visual recognition challenge. https:\/\/cs231n.stanford.edu\/reports\/2015\/pdfs\/yle_project.pdf."},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"B63","first-page":"8847","volume":"33","author":"Levy D","year":"2020","journal-title":"Adv. Neural Inform. Processing Systems"},{"issue":"137","key":"B64","first-page":"1","volume":"23","author":"Lin T","year":"2022","journal-title":"J. Machine Learn. Res."},{"key":"B65","first-page":"9383","volume":"33","author":"Lin T","year":"2020","journal-title":"Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Adv. Neural Inform. Processing Systems"},{"key":"B66","doi-asserted-by":"publisher","DOI":"10.4208\/nmtma.OA-2020-0125"},{"key":"B67","author":"Luise G","year":"2018","journal-title":"Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds. Adv. Neural Inform. Processing Systems, vol. 31 (Curran Associates, Inc., Red Hook, NY), 1\u201312."},{"key":"B68","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.03.008"},{"key":"B69","unstructured":"Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2018) Towards deep learning models resistant to adversarial attacks.\n                      Internat. Conf. Learn. Representations\n                      (OpenReview.net), 1\u201323."},{"key":"B70","first-page":"1657","volume":"33","author":"Mensch A","year":"2020","journal-title":"Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Adv. Neural Inform. Processing Systems"},{"key":"B71","first-page":"2208","volume":"29","author":"Namkoong H","year":"2016","journal-title":"Lee D, Sugiyama M, Luxburg U, Guyon I, Garnett R, eds. Adv. Neural Inform. Processing Systems"},{"key":"B72","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1080.0951"},{"key":"B73","volume-title":"Problem Complexity and Method Efficiency in Optimization","author":"Nemirovsky A","year":"1983"},{"key":"B74","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970791"},{"key":"B75","unstructured":"Nguyen VA, Si N, Blanchet J (2020) Robust Bayesian classification using an optimistic score ratio. Daum\u00e9 H III, Singh A, eds.\n                      Internat. Conf. Machine Learn.\n                      , vol. 119 (PMLR, New York), 7327\u20137337."},{"key":"B76","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0243"},{"key":"B77","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Wu X, Jha S, Swami A (2016a) Distillation as a defense to adversarial perturbations against deep neural networks.\n                      2016 IEEE Sympos. Security Privacy\n                      (IEEE, Piscataway, NJ), 582\u2013597.","DOI":"10.1109\/SP.2016.41"},{"key":"B78","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Goodfellow I, Jha S, Celik ZB, Swami A (2017) Practical black-box attacks against machine learning.\n                      Proc. 2017 ACM Asia Conf. Comput. Comm. Security\n                      (Association for Computing Machinery, New York), 506\u2013519.","DOI":"10.1145\/3052973.3053009"},{"key":"B79","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Jha S, Fredrikson M, Celik ZB, Swami A (2016b) The limitations of deep learning in adversarial settings.\n                      2016 IEEE Eur. Sympos. Security Privacy\n                      (IEEE, Piscataway, NJ), 372\u2013387.","DOI":"10.1109\/EuroSP.2016.36"},{"key":"B80","first-page":"733","volume-title":"Uncertainty in Artificial Intelligence","author":"Patrini G","year":"2020"},{"key":"B81","unstructured":"Petzka H, Fischer A, Lukovnikov D (2018) On the regularization of Wasserstein GANs.\n                      Internat. Conf. Learn. Representations\n                      (OpenReview.net), 1\u201324."},{"key":"B82","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"B83","doi-asserted-by":"publisher","DOI":"10.1080\/14697680701455410"},{"key":"B84","doi-asserted-by":"publisher","DOI":"10.1137\/21M1390517"},{"key":"B85","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0137"},{"key":"B86","volume-title":"Trans. Machine Learn. Res.","author":"Qi Q","year":"2025"},{"key":"B87","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"B88","doi-asserted-by":"crossref","unstructured":"Rozsa A, Gunther M, Boult TE (2018) Towards robust deep neural networks with bang.\n                      2018 IEEE Winter Conf. Appl. Comput. Vision\n                      (IEEE, Piscataway, NJ), 803\u2013811.","DOI":"10.1109\/WACV.2018.00093"},{"key":"B89","volume-title":"Studies in the Mathematical Theory of Inventory and Production","author":"Scarf H","year":"1957"},{"key":"B90","author":"Selvi A","year":"2022","journal-title":"Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A, eds. Adv. Neural Inform. Processing Systems, vol. 35 (Curran Associates, Inc., Red Hook, NY), 1\u201314."},{"issue":"103","key":"B91","first-page":"1","volume":"20","author":"Shafieezadeh-Abadeh S","year":"2019","journal-title":"J. Machine Learn. Res."},{"key":"B92","volume":"28","author":"Shafieezadeh Abadeh S","year":"2015","journal-title":"Cortes C, Lawrence N, Lee D, Sugiyama M, Garnett R, eds. Adv. Neural Inform. Processing Systems"},{"key":"B93","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":"B94","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3403-4_7"},{"key":"B95","doi-asserted-by":"publisher","DOI":"10.1137\/21M1465548"},{"key":"B96","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2020.12.001"},{"key":"B97","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-022-09832-9"},{"key":"B98","unstructured":"Sinha A, Namkoong H, Duchi J (2018) Certifiable distributional robustness with principled adversarial training.\n                      Internat. Conf. Learn. Representations\n                      (OpenReview.net), 1\u201334."},{"key":"B99","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703591"},{"key":"B100","volume-title":"Trans. Machine Learn. Res.","author":"Song J","year":"2025"},{"key":"B101","first-page":"9134","volume":"32","author":"Staib M","year":"2019","journal-title":"Adv. Neural Inform. Processing Systems"},{"key":"B102","unstructured":"Tram\u00e8r F, Kurakin A, Papernot N, Goodfellow I, Boneh D, McDaniel P (2018) Ensemble adversarial training: Attacks and defenses.\n                      Internat. Conf. Learn. Representations\n                      (OpenReview.net), 1\u201320."},{"key":"B103","doi-asserted-by":"publisher","DOI":"10.1137\/1038003"},{"key":"B104","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0878-1"},{"key":"B105","unstructured":"Wang J, Gao R, Xie Y (2022a) Two-sample test with kernel projected Wasserstein distance. Camps-Valls G, Ruiz F, Valera I, eds.\n                      Proc. 25th Internat. Conf. Artificial Intelligence Statist.\n                      , vol. 151 (PMLR, New York), 8022\u20138055."},{"key":"B106","author":"Wang J","year":"2022","journal-title":"Oper. Res."},{"key":"B107","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-015-0240-3"},{"key":"B108","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2844356"},{"key":"B109","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2014.1314"},{"key":"B110","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-010-0812-0"},{"issue":"1","key":"B111","first-page":"115","volume":"186","author":"Xie W","year":"2019","journal-title":"Math. Programming"},{"key":"B112","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2017.2711553"},{"key":"B113","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3030884"},{"key":"B114","unstructured":"Yu Y, Lin T, Mazumdar EV, Jordan M (2022) Fast distributionally robust learning with variance-reduced min-max optimization. Camps-Valls G, Ruiz F, Valera I, eds.\n                      Internat. Conf. Artificial Intelligence Statist.\n                      , vol. 151 (PMLR, New York), 1219\u20131250."},{"key":"B115","doi-asserted-by":"publisher","DOI":"10.2307\/2340126"},{"key":"B116","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2018.01.011"},{"key":"B117","unstructured":"Zhu J, Jitkrittum W, Diehl M, Sch\u00f6lkopf B (2021) Kernel distributionally robust optimization: Generalized duality theorem and stochastic approximation. Banerjee A, Fukumizu K, eds.\n                      Proc. 24th Internat. Conf. Artificial Intelligence Statist.\n                      , vol. 130 (PMLR, New York), 280\u2013288."},{"key":"B118","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-011-0494-7"}],"container-title":["Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/opre.2023.0294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T08:17:04Z","timestamp":1779697024000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/opre.2023.0294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":118,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1287\/opre.2023.0294"],"URL":"https:\/\/doi.org\/10.1287\/opre.2023.0294","relation":{},"ISSN":["0030-364X","1526-5463"],"issn-type":[{"value":"0030-364X","type":"print"},{"value":"1526-5463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}