{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T11:32:29Z","timestamp":1785238349248,"version":"3.55.0"},"reference-count":94,"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>Nature Doesn\u2019t Play Dice, It Plays to Win<\/jats:p>\n                  <jats:p>Decision making under uncertainty can be brittle, often failing when real-world data deviates from training assumptions. This study frames this problem as a game between a decision maker and an adversary, nature, who strategically corrupts the data distribution to create a worst case scenario with the cost of these changes defined by optimal transport theory. The authors establish conditions under which a stable outcome, a Nash equilibrium, exists and provide efficient methods to compute it. A key insight is that nature\u2019s optimal strategy corresponds to generating remarkably deceptive adversarial examples; in an image classification task, this strategy can transform an image of an \u201c8\u201d into a convincing \u201c3.\u201d This work provides a powerful framework for developing more reliable models by understanding and countering worst case data perturbations.<\/jats:p>","DOI":"10.1287\/opre.2023.0138","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T13:52:22Z","timestamp":1766152342000},"page":"1689-1709","source":"Crossref","is-referenced-by-count":2,"title":["Nash Equilibria, Regularization, and Computation in Optimal Transport-Based Distributionally Robust Optimization"],"prefix":"10.1287","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9095-2686","authenticated-orcid":false,"given":"Soroosh","family":"Shafiee","sequence":"first","affiliation":[{"name":"Operations Research and Information Engineering, Cornell University, Ithaca, New York 14850"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6710-3723","authenticated-orcid":false,"given":"Liviu","family":"Aolaritei","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, California 94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9649-5305","authenticated-orcid":false,"given":"Florian","family":"D\u00f6rfler","sequence":"additional","affiliation":[{"name":"Automatic Control Lab, Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich, 8092 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2697-8886","authenticated-orcid":false,"given":"Daniel","family":"Kuhn","sequence":"additional","affiliation":[{"name":"Risk Analytics and Optimization Chair, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"109","reference":[{"key":"B1","unstructured":"Aolaritei L, Shafiee S, D\u00f6rfler F (2022) Wasserstein distributionally robust estimation in high dimensions: Performance analysis and optimal hyperparameter tuning. Preprint, submitted June 27, https:\/\/doi.org\/10.48550\/arXiv.2206.13269."},{"key":"B2","doi-asserted-by":"crossref","unstructured":"Aolaritei L, Fochesato M, Lygeros J, D\u00f6rfler F (2023) Wasserstein tube MPC with exact uncertainty propagation.\n                      Conf. Decision Control\n                      (IEEE, Piscataway, NJ)\n                      ,\n                      2036\u20132041.","DOI":"10.1109\/CDC49753.2023.10383526"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2025.3567559"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/s0294-1449(16)30214-1"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/s0294-1449(17)30036-7"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.4064\/sm-7-1-36-44"},{"key":"B7","doi-asserted-by":"crossref","unstructured":"Bartl D, Drapeau S, Ob\u0142\u00f3j J, Wiesel J (2021) Sensitivity analysis of Wasserstein distributionally robust optimization problems.\n                      Proc. Roy. Soc. A\n                      477:20210176.","DOI":"10.1098\/rspa.2021.0176"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9467-7"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1162\/JEEA.2008.6.2-3.560"},{"key":"B10","volume-title":"Convergence of Probability Measures","author":"Billingsley P","year":"2013"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2018.0936"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1017\/jpr.2019.49"},{"key":"B15","first-page":"11817","author":"Blanchet J","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asab026"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1178"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3014098"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9045(91)90062-F"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1137\/090769521"},{"issue":"1","key":"B19","first-page":"517","volume":"19","author":"Chen R","year":"2018","journal-title":"J. Machine Learn. Res."},{"key":"B20","first-page":"749","author":"Chen R","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2330"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3097706"},{"key":"B23","volume-title":"Elements of Information Theory","author":"Cover T","year":"2006"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810756"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2004"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2020.1085"},{"key":"B27","first-page":"4240","author":"Farnia F","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B28","first-page":"100017","volume":"3","author":"Finlay C","year":"2021","journal-title":"Machine Learn. Appl."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2326"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1275"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2383"},{"key":"B32","unstructured":"Gao R, Xie L, Xie Y, Xu H (2018) Robust hypothesis testing using Wasserstein uncertainty sets. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc, Red Hook, NY), 7902\u20137912."},{"key":"B33","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. Preprint, submitted December 20, https:\/\/doi.org\/10.48550\/arXiv.1412.6572."},{"key":"B34","unstructured":"Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of Wasserstein GANs. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc, Red Hook, NY), 5769\u20135779."},{"key":"B35","unstructured":"Hein M, Andriushchenko M (2017) Formal guarantees on the robustness of a classifier against adversarial manipulation. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc, Red Hook, NY), 2263\u20132273."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(80)90246-2"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01796-6"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01605-y"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1287\/ijoo.2022.0083"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2315156"},{"key":"B41","doi-asserted-by":"crossref","unstructured":"Jakubovitz D, Giryes R (2018) Improving DNN robustness to adversarial attacks using Jacobian regularization. Ferrari V, Hebert M, Sminchisescu C, Weiss Y, eds.\n                      Eur. Conf. Comput. Vision\n                      (Springer\n                      ,\n                      Berlin), 514\u2013529.","DOI":"10.1007\/978-3-030-01258-8_32"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-021-01615-4"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3219"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492924000084"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2019.0198"},{"key":"B46","unstructured":"Kwon Y, Kim W, Won J-H, Paik MC (2020) Principled learning method for Wasserstein distributionally robust optimization with local perturbations. Daum\u00e9 III H, Singh A, eds.\n                      Internat. Conf. Machine Learn\n                      (PMLR, New York), 5567\u20135576."},{"issue":"4","key":"B47","first-page":"1090","volume":"67","author":"Lam H","year":"2019","journal-title":"Oper. Res."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/S0047-259X(03)00096-4"},{"key":"B50","unstructured":"Lee J, Raginsky M (2018) Minimax statistical learning with Wasserstein distances. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc, Red Hook, NY), 2687\u20132696."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2271852"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2237919"},{"key":"B53","volume-title":"Theory of Point Estimation","author":"Lehmann EL","year":"2006"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.821992"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2219952"},{"key":"B56","doi-asserted-by":"crossref","unstructured":"Lyu C, Huang K, Liang H-N (2015) A unified gradient regularization family for adversarial examples.\n                      Internat. Conf. Data Mining\n                      (IEEE, Piscataway, NJ), 301\u2013309.","DOI":"10.1109\/ICDM.2015.84"},{"key":"B57","unstructured":"M\u0105dry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2018) Towards deep learning models resistant to adversarial attacks.\n                      Internat. Conf. Learn. Representations\n                      (MIT Press, Cambridge, MA)."},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01416-w"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1216-6"},{"key":"B61","unstructured":"Nagarajan V, Kolter JZ (2017) Gradient descent GAN optimization is locally stable. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc., Red Hook, NY), 5591\u20135600."},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2076"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1176"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00928"},{"key":"B65","unstructured":"Papernot N, McDaniel P, Goodfellow I (2016a) Transferability in machine learning: From phenomena to black-box attacks using adversarial samples. Preprint, submitted May 24, https:\/\/arxiv.org\/abs\/1605.07277."},{"key":"B66","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Wu X, Jha S, Swami A (2016b) Distillation as a defense to adversarial perturbations against deep neural networks.\n                      IEEE Sympos. Security Privacy\n                      (IEEE, Piscataway, NJ), 582\u2013597.","DOI":"10.1109\/SP.2016.41"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"B68","doi-asserted-by":"publisher","DOI":"10.1006\/jath.1998.3201"},{"key":"B69","volume-title":"Introduction to Optimization","author":"Polyak B","year":"1987"},{"key":"B70","volume-title":"Variational Analysis","author":"Rockafellar RT","year":"2009"},{"key":"B71","unstructured":"Roth K, Lucchi A, Nowozin S, Hofmann T (2017) Stabilizing training of generative adversarial networks through regularization. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc., Red Hook, NY)\n                      ,\n                      2018\u20132028."},{"key":"B72","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2015.2228"},{"issue":"103","key":"B73","first-page":"1","volume":"20","author":"Shafieezadeh-Abadeh S","year":"2019","journal-title":"J. Machine Learn. Res."},{"key":"B74","unstructured":"Shafieezadeh-Abadeh S, Mohajerin Esfahani P, Kuhn D (2015) Distributionally robust logistic regression. Cortes C, Lawrence N, Lee D, Sugiyama M, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc., Red Hook, NY), 1576\u20131584."},{"key":"B75","unstructured":"Shafieezadeh-Abadeh S, Nguyen VA, Kuhn D, Mohajerin Esfahani P (2018) Wasserstein distributionally robust Kalman filtering. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc., Red Hook, NY)\n                      ,\n                      8474\u20138483."},{"key":"B76","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973433"},{"key":"B77","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01788-6"},{"key":"B78","unstructured":"Sinha A, Namkoong H, Duchi J (2018) Certifying some distributional robustness with principled adversarial training.\n                      Internat. Conf. Learn. Representations\n                      (ICLR, Appleton, WI)."},{"key":"B79","unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow IJ, Fergus R (2013) Intriguing properties of neural networks. Preprint, submitted December 21, https:\/\/doi.org\/10.48550\/arXiv.1312.6199."},{"key":"B80","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01856-x"},{"key":"B81","unstructured":"Tu Z, Zhang J, Tao D (2019) Theoretical analysis of adversarial learning: A minimax approach. Wallach H, Larochelle H, Beygelzimer A, d\u2019Alch\u00e9-Buc F, Fox E, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      (Curran Associates Inc., Red Hook, NY), 12280\u201312290."},{"key":"B82","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2020.3678"},{"key":"B83","doi-asserted-by":"publisher","DOI":"10.4467\/20838476SI.18.003.10408"},{"key":"B84","volume-title":"Optimal Transport: Old and New","author":"Villani C","year":"2008"},{"key":"B85","unstructured":"Volpi R, Namkoong H, Sener O, Duchi J, Murino V, Savarese S (2018) Generalizing to unseen domains via adversarial data augmentation. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds.\n                      Adv. Neural Inform. Processing Systems\n                      (Curran Associates Inc., Red Hook, NY)\n                      ,\n                      5339\u20135349."},{"key":"B86","unstructured":"Wang Y, Ma X, Bailey J, Yi J, Zhou B, Gu Q (2019) On the convergence and robustness of adversarial training. Chaudhuri K, Salakhutdinov R, eds.\n                      Internat. Conf. Machine Learn.\n                      (PMLR, New York), 6586\u20136595."},{"key":"B87","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01445-5"},{"key":"B88","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3030884"},{"key":"B89","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-021-01673-8"},{"key":"B90","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.0135"},{"key":"B91","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2018.01.011"},{"key":"B92","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0268"},{"key":"B93","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2601879"},{"key":"B94","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.06.005"}],"container-title":["Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/opre.2023.0138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T08:17:25Z","timestamp":1779697045000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/opre.2023.0138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":94,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1287\/opre.2023.0138"],"URL":"https:\/\/doi.org\/10.1287\/opre.2023.0138","relation":{},"ISSN":["0030-364X","1526-5463"],"issn-type":[{"value":"0030-364X","type":"print"},{"value":"1526-5463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}