{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T16:00:07Z","timestamp":1776700807334,"version":"3.51.2"},"reference-count":78,"publisher":"Informa UK Limited","issue":"5","license":[{"start":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T00:00:00Z","timestamp":1631145600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"crossref","award":["18-71-10108"],"award-info":[{"award-number":["18-71-10108"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012190","name":"Ministry of Science and Higher Education of the Russian Federation","doi-asserted-by":"crossref","award":["075-00337-20-03"],"award-info":[{"award-number":["075-00337-20-03"]}],"id":[{"id":"10.13039\/501100012190","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012190","name":"Ministry of Science and Higher Education of the Russian Federation","doi-asserted-by":"crossref","award":["0714-2020-0005"],"award-info":[{"award-number":["0714-2020-0005"]}],"id":[{"id":"10.13039\/501100012190","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Optimization Methods and Software"],"published-print":{"date-parts":[[2022,9,3]]},"DOI":"10.1080\/10556788.2021.1965600","type":"journal-article","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T06:46:03Z","timestamp":1631256363000},"page":"1603-1635","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":6,"title":["Stochastic approximation versus sample average approximation for Wasserstein barycenters"],"prefix":"10.1080","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1757-1021","authenticated-orcid":false,"given":"Darina","family":"Dvinskikh","sequence":"first","affiliation":[{"name":"Weierstrass Institute for Applied Analysis and Stochastics, Berlin, Germany"},{"name":"Moscow Institute of Physics and Technology, Dolgoprudny, Russia"},{"name":"Institute for Information Transmission Problems, Moscow, Russia"}]}],"member":"301","published-online":{"date-parts":[[2021,9,9]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1137\/100805741"},{"key":"CIT0002","unstructured":"R.K. Ahuja, T.L. Magnanti, and J.B. Orlin, Network flows: Theory, Algorithms, and Applications 526, 1993."},{"key":"CIT0003","unstructured":"J. Altschuler, J. Weed, and P. Rigollet, Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration, in Advances in Neural Information Processing Systems 30, I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, eds., Curran Associates, Inc., 2017, pp. 1961\u20131971. Available at http:\/\/papers.nips.cc\/paper\/6792-near-linear-time-approximation-algorithms-for-optimal-transport-via-sinkhorn-iteration.pdf, arXiv:1705.09634."},{"key":"CIT0004","unstructured":"M. Arjovsky, S. Chintala, and L. Bottou, Wasserstein GAN, preprint (2017), arXiv:1701.07875."},{"key":"CIT0005","unstructured":"M. Ballu, Q. Berthet, and F. Bach, Stochastic optimization for regularized Wasserstein estimators, preprint (2020), arXiv:2002.08695."},{"key":"CIT0006","doi-asserted-by":"crossref","unstructured":"A. Ben-Tal and A. Nemirovski, Lectures on Modern Convex Optimization, Society for Industrial and Applied Mathematics, 2001. Available at http:\/\/epubs.siam.org\/doi\/abs\/10\u00a0.1137\/1.9780898718829.","DOI":"10.1137\/1.9780898718829"},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1137\/141000439"},{"key":"CIT0008","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz023"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1214\/19-EJS1637"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1137\/18M1185065"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1214\/18-EJS1400"},{"key":"CIT0012","unstructured":"J. Bigot and T. Klein, Characterization of barycenters in the Wasserstein space by averaging optimal transport maps, preprint (2012), arXiv:1212.2562."},{"key":"CIT0013","unstructured":"J. Bigot and T. Klein, et\u00a0al. Consistent estimation of a population barycenter in the Wasserstein space, preprint (2012), ArXiv e-prints."},{"key":"CIT0014","unstructured":"J. Blanchet, A. Jambulapati, C. Kent, and A. Sidford, Towards optimal running times for optimal transport, preprint (2018), arXiv:1810.07717."},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.3150\/13-BEJ585"},{"key":"CIT0016","unstructured":"G. Carlier, On the linear convergence of the multi-marginal Sinkhorn algorithm, (2021)."},{"key":"CIT0017","unstructured":"S. Chewi, T. Maunu, P. Rigollet, and A.J. Stromme, Gradient descent algorithms for Bures\u2013Wasserstein barycenters, preprint (2020), arXiv:2001.01700."},{"key":"CIT0018","unstructured":"M. Cuturi, Sinkhorn distances: Lightspeed computation of optimal transport, in Advances in Neural Information Processing Systems 26, C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, eds., Curran Associates, Inc., 2013, pp. 2292\u20132300. Available at http:\/\/papers.nips.cc\/paper\/4927-sinkhorn-distances-lightspeed-computation-of-optimal-transport.pdf."},{"key":"CIT0019","doi-asserted-by":"publisher","DOI":"10.1137\/15M1032600"},{"key":"CIT0020","doi-asserted-by":"publisher","DOI":"10.1145\/3188745.3188826"},{"key":"CIT0021","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-018-9800-z"},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.1137\/19M1301047"},{"key":"CIT0023","unstructured":"Y. Dong, Y. Gao, R. Peng, I. Razenshteyn, and S. Sawlani, A study of performance of optimal transport, preprint (2020), arXiv:2005.01182."},{"key":"CIT0024","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390191"},{"key":"CIT0025","unstructured":"D. Dvinskikh and D. Tiapkin, Improved complexity bounds in wasserstein barycenter problem, in Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021, pp. 1738\u20131746."},{"key":"CIT0026","unstructured":"P. Dvurechensky, A. Gasnikov, and A. Kroshnin, Computational optimal transport: complexity by accelerated gradient descent is better than by Sinkhorns algorithm, in Proceedings of the 35th International Conference on Machine Learning, J. Dy and A. Krause, eds., Vol. 80, 2018, pp. 1367\u20131376. arXiv:1802.04367."},{"key":"CIT0027","unstructured":"J. Ebert, V. Spokoiny, and A. Suvorikova, Construction of non-asymptotic confidence sets in 2-Wasserstein space, preprint (2017). arXiv:1703.03658."},{"key":"CIT0028","unstructured":"V. Feldman and J. Vondr\u00e1k, High probability generalization bounds for uniformly stable algorithms with nearly optimal rate, preprint (2019). arXiv:1902.10710."},{"key":"CIT0029","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(89)90490-4"},{"key":"CIT0030","unstructured":"M. Fr\u00e9chet, Les \u00e9l\u00e9ments al\u00e9atoires de nature quelconque dans un espace distanci\u00e9, in Annales de l'institut Henri Poincar\u00e9 10, 1948, pp. 215\u2013310."},{"key":"CIT0031","unstructured":"C. Frogner, C. Zhang, H. Mobahi, M. Araya, and T.A. Poggio, Learning with a Wasserstein loss, in Advances in Neural Information Processing Systems, 2015, pp. 2053\u20132061."},{"key":"CIT0032","doi-asserted-by":"publisher","DOI":"10.1145\/115234.115366"},{"key":"CIT0033","unstructured":"A. Gasnikov, P. Dvurechensky, D. Kamzolov, Y. Nesterov, V. Spokoiny, P. Stetsyuk, A. Suvorikova, and A. Chernov, Universal method with inexact oracle and its applications for searching equillibriums in multistage transport problems, preprint (2015), arXiv:1506.00292."},{"key":"CIT0034","doi-asserted-by":"publisher","DOI":"10.1134\/S0005117916110114"},{"key":"CIT0035","unstructured":"A. Genevay, G. Peyr\u00e9, and M. Cuturi, Learning generative models with Sinkhorn divergences, preprint (2017), arXiv:1706.00292."},{"key":"CIT0036","unstructured":"E. Gorbunov, D. Dvinskikh, and A. Gasnikov, Optimal decentralized distributed algorithms for stochastic convex optimization, preprint (2019), arXiv:1911.07363."},{"key":"CIT0037","unstructured":"T.L. Gouic, Q. Paris, P. Rigollet, and A.J. Stromme, Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space, preprint (2019), arXiv:1908.00828."},{"key":"CIT0038","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19992-4_20"},{"key":"CIT0039","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2017.1350177"},{"key":"CIT0040","unstructured":"S. Guminov, P. Dvurechensky, N. Tupitsa, and A. Gasnikov, Accelerated alternating minimization, preprint (2019). arXiv:1906.03622."},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"CIT0042","unstructured":"A. Jambulapati, A. Sidford, and K. Tian, A direct  O~(1\/\u03f5) iteration parallel algorithm for optimal transport, in Advances in Neural Information Processing Systems, 2019, pp. 11359\u201311370."},{"key":"CIT0043","unstructured":"A. Juditsky, J. Kwon, and \u00c9. Moulines, Unifying mirror descent and dual averaging, preprint (2019). arXiv:1910.13742."},{"key":"CIT0044","unstructured":"A. Juditsky and A. Nemirovski, First order methods for non-smooth convex large-scale optimization, i: General purpose methods, in Optimization for Machine Learning, S.W. Suvrit Sra Sebastian Nowozin, ed., Cambridge, MA: MIT Press, 2012, pp. 121\u2013184."},{"key":"CIT0045","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOS546"},{"key":"CIT0046","unstructured":"S.M. Kakade and A. Tewari, On the generalization ability of online strongly convex programming algorithms, in Advances in Neural Information Processing Systems, 2009, pp. 801\u2013808."},{"key":"CIT0047","doi-asserted-by":"publisher","DOI":"10.1137\/19M1278788"},{"key":"CIT0048","unstructured":"Y. Klochkov and N. Zhivotovskiy, Stability and deviation optimal risk bounds with convergence rate O(1\/n), (2021), arXiv preprint. arXiv:2103.12024."},{"key":"CIT0049","unstructured":"A. Kroshnin, V. Spokoiny, and A. Suvorikova, Statistical inference for Bures\u2013Wasserstein barycenters, preprint (2019), arXiv:1901.00226."},{"key":"CIT0050","unstructured":"A. Kroshnin, N. Tupitsa, D. Dvinskikh, P. Dvurechensky, A. Gasnikov, and C. Uribe, On the Complexity of Approximating Wasserstein Barycenters, in Proceedings of the 36th International Conference on Machine Learning, K. Chaudhuri and R. Salakhutdinov, eds., Vol. 97, 2019, pp. 3530\u20133540. arXiv:1901.08686."},{"key":"CIT0051","unstructured":"M. Kusner, Y. Sun, N. Kolkin, and K. Weinberger, From word embeddings to document distances, in International conference on machine learning, PMLR, 2015, pp. 957\u2013966."},{"key":"CIT0052","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-016-0727-z"},{"key":"CIT0053","doi-asserted-by":"crossref","unstructured":"Y.T. Lee and A. Sidford, Path finding methods for linear programming: Solving linear programs in  O~(rank) iterations and faster algorithms for maximum flow, in 2014 IEEE 55th Annual Symposium on Foundations of Computer Science, 2014 Oct, pp. 424\u2013433.","DOI":"10.1109\/FOCS.2014.52"},{"key":"CIT0054","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"CIT0055","doi-asserted-by":"crossref","unstructured":"Y. Nesterov, Primal-dual subgradient methods for convex problems, in Mathematical Programming 120, (2009), pp. 221\u2013259. Available at https:\/\/doi.org\/10.1007\/s10107-007-0149-x, First appeared in 2005 as CORE discussion paper 2005\/67.","DOI":"10.1007\/s10107-007-0149-x"},{"key":"CIT0056","unstructured":"F. Orabona, A modern introduction to online learning, preprint (2019), arXiv:1912.13213."},{"key":"CIT0057","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-030718-104938"},{"key":"CIT0058","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"CIT0059","unstructured":"K. Quanrud, Approximating optimal transport with linear programs, preprint (2018), arXiv:1810.05957."},{"key":"CIT0060","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18461-6_21"},{"key":"CIT0061","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24785-9_37"},{"key":"CIT0062","doi-asserted-by":"publisher","DOI":"10.1002\/9781444392715"},{"key":"CIT0063","unstructured":"G. Rios, J. Backhoff-Veraguas, J. Fontbona, and F. Tobar, Bayesian learning with Wasserstein barycenters, ArXiv e-prints (2018)."},{"key":"CIT0064","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"CIT0065","unstructured":"A. Rolet, M. Cuturi, and G. Peyr\u00e9, Fast dictionary learning with a smoothed Wasserstein loss, in Artificial Intelligence and Statistics, 2016, pp. 630\u2013638."},{"key":"CIT0066","unstructured":"Y. Rubner, C. Tomasi, and L.J. Guibas, A metric for distributions with applications to image databases, in 6th International Conference on Computer Vision (IEEE Cat. No. 98CH36271), IEEE, 1998, pp. 59\u201366."},{"key":"CIT0067","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"CIT0068","doi-asserted-by":"crossref","unstructured":"S. Shalev-Shwartz, O. Shamir, N. Srebro, and K. Sridharan, Stochastic convex optimization, in COLT, 2009.","DOI":"10.1145\/1390156.1390273"},{"key":"CIT0069","doi-asserted-by":"crossref","unstructured":"A. Shapiro, D. Dentcheva, and A. Ruszczyski, Lectures on Stochastic Programming, Society for Industrial and Applied Mathematics, 2009, Available at http:\/\/epubs.siam.org\/doi\/abs\/10\u00a0.1137\/1.9780898718751.","DOI":"10.1137\/1.9780898718751"},{"key":"CIT0070","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-26771-9_4"},{"key":"CIT0071","doi-asserted-by":"publisher","DOI":"10.1145\/2766963"},{"key":"CIT0072","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12236"},{"key":"CIT0073","doi-asserted-by":"publisher","DOI":"10.1214\/12-AOS1054"},{"key":"CIT0074","unstructured":"S. Srivastava, V. Cevher, Q. Dinh, and D. Dunson, WASP: Scalable Bayes via barycenters of subset posteriors, in Artificial Intelligence and Statistics, PMLR, (2015), pp. 912\u2013920."},{"key":"CIT0075","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22629-9_8"},{"key":"CIT0076","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-017-0726-4"},{"key":"CIT0077","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2089693"},{"key":"CIT0078","doi-asserted-by":"publisher","DOI":"10.3150\/18-BEJ1065"}],"container-title":["Optimization Methods and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/10556788.2021.1965600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T14:55:06Z","timestamp":1671202506000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/10556788.2021.1965600"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,9]]},"references-count":78,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,9,3]]}},"alternative-id":["10.1080\/10556788.2021.1965600"],"URL":"https:\/\/doi.org\/10.1080\/10556788.2021.1965600","relation":{},"ISSN":["1055-6788","1029-4937"],"issn-type":[{"value":"1055-6788","type":"print"},{"value":"1029-4937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,9]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=goms20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=goms20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2020-09-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}