{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:37Z","timestamp":1792786897193,"version":"4.5.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology Major Project","award":["2022ZD0114801"],"award-info":[{"award-number":["2022ZD0114801"]}]},{"name":"NSFC","award":["62361146852"],"award-info":[{"award-number":["62361146852"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Ministry of Education of China","award":["JYB2025XDXM118"],"award-info":[{"award-number":["JYB2025XDXM118"]}],"id":[{"id":"https:\/\/ror.org\/03m01yf64","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3703554","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:46:54Z","timestamp":1781552814000},"page":"12880-12891","source":"Crossref","is-referenced-by-count":0,"title":["Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5138-3182","authenticated-orcid":false,"given":"Lijun","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5602-4844","authenticated-orcid":false,"given":"Haomin","family":"Bai","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7925-8255","authenticated-orcid":false,"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0746-1494","authenticated-orcid":false,"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"ref2","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","author":"Kushner","year":"2003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/16M1058297"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2020.1085"},{"key":"ref7","first-page":"2029","article-title":"Does distributionally robust supervised learning give robust classifiers?","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Hu"},{"key":"ref8","first-page":"1036","article-title":"Adaptive sampling for stochastic risk-averse learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Curi"},{"key":"ref9","first-page":"2771","article-title":"Non-convex distributionally robust optimization: Non-asymptotic analysis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref10","first-page":"2704","article-title":"Minimax regret optimization for robust machine learning under distribution shift","volume-title":"Proc. 35th Conf. Learn. Theory","author":"Agarwal"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1432"},{"key":"ref12","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa"},{"key":"ref13","first-page":"4615","article-title":"Agnostic federated learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Mohri"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0030"},{"key":"ref16","article-title":"Optimal algorithms for group distributionally robust optimization and beyond","author":"Soma","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2599"},{"key":"ref18","first-page":"3168","article-title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Neu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref20","first-page":"793","article-title":"Minimizing the maximal loss: How and why","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Shalev-Shwartz"},{"key":"ref21","first-page":"497","article-title":"Learning with average top-k loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2286"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1057\/9781137024381_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1515\/9781400831050"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1374"},{"key":"ref26","article-title":"Certifying some distributional robustness with principled adversarial training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sinha"},{"key":"ref27","first-page":"1929","article-title":"Fairness without demographics in repeated loss minimization","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Hashimoto"},{"key":"ref28","first-page":"10544","article-title":"Class-weighted classification: Trade-offs and robust approaches","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00936"},{"key":"ref30","article-title":"Coping with label shift via distributionally robust optimisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0741"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2019.0198"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.0294"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1174-z"},{"key":"ref35","first-page":"46073","article-title":"Beyond minimax rates in group distributionally robust optimization via a novel notion of sparsity","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref36","first-page":"1283","article-title":"On distributionally robust optimization and data rebalancing","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist.","author":"S\u0142owik"},{"key":"ref37","first-page":"58599","article-title":"Efficient stochastic approximation of minimax excess risk optimization","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref38","first-page":"57384","article-title":"Efficient algorithms for empirical group distributionally robust optimization and beyond","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref39","first-page":"2389","article-title":"Collaborative PAC learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Blum"},{"key":"ref40","first-page":"7642","article-title":"Improved algorithms for collaborative PAC learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref41","first-page":"9107","article-title":"Multi-group agnostic PAC learnability","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Rothblum"},{"key":"ref42","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2890018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01442-2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"issue":"3","key":"ref47","first-page":"73","article-title":"Using anytime algorithms in intelligent systems","volume":"17","author":"Zilberstein","year":"1996","journal-title":"AI Mag."},{"key":"ref48","first-page":"1446","article-title":"Anytime online-to-batch, optimism and acceleration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Cutkosky"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1006\/game.1999.0738"},{"key":"ref50","first-page":"2989","article-title":"Fast convergence of regularized learning in games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Syrgkanis"},{"key":"ref51","article-title":"Efficient online-bandit strategies for minimax learning problems","author":"Roux","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref54","first-page":"613","article-title":"Efficient learning by implicit exploration in bandit problems with side observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Koc\u00e1k"},{"key":"ref55","article-title":"A modern introduction to online learning","author":"Orabona","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0030"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3605209"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2013.0598"},{"issue":"154","key":"ref59","first-page":"1","article-title":"Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits","volume":"17","author":"Neu","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2928952"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1147954.1147956"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16108-7_30"},{"key":"ref63","article-title":"Adult","author":"Becker","year":"1996"},{"key":"ref64","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010"},{"key":"ref65","first-page":"2971","article-title":"Variance-based regularization with convex objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Namkoong"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"ref67","first-page":"2216","article-title":"Stochastic gradient methods for distributionally robust optimization with $f$f-divergences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Namkoong"},{"key":"ref68","first-page":"8847","article-title":"Large-scale methods for distributionally robust optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Levy"},{"key":"ref69","first-page":"10067","article-title":"An online method for a class of distributionally robust optimization with non-convex objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2021.1895152"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01056-8"},{"key":"ref72","first-page":"640","article-title":"Predict then interpolate: A simple algorithm to learn stable classifiers","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref74","first-page":"385","article-title":"Online convex optimization in the bandit setting: Gradient descent without a gradient","volume-title":"Proc. 16th Annu. ACM-SIAM Symp. Discrete Algorithms","author":"Flaxman"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11563655.pdf?arnumber=11563655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:02:59Z","timestamp":1790265779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11563655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":75,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3703554","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}