{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T14:27:24Z","timestamp":1772720844191,"version":"3.50.1"},"reference-count":61,"publisher":"Informa UK Limited","issue":"6","funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-21-1-2244"],"award-info":[{"award-number":["N00014-21-1-2244"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-24-1-2628"],"award-info":[{"award-number":["N00014-24-1-2628"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1814888"],"award-info":[{"award-number":["CCF-1814888"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-2053485"],"award-info":[{"award-number":["DMS-2053485"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Optimization Methods and Software"],"published-print":{"date-parts":[[2025,11,2]]},"DOI":"10.1080\/10556788.2025.2549356","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T01:38:41Z","timestamp":1771465121000},"page":"1535-1583","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Entropic risk-averse generalized momentum methods"],"prefix":"10.1080","volume":"40","author":[{"given":"Bugra","family":"Can","sequence":"first","affiliation":[{"name":"Amazon Web Services","place":["New York, USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mert","family":"G\u00fcrb\u00fczbalaban","sequence":"additional","affiliation":[{"name":"Rutgers University","place":["Piscataway, USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2026,2,18]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_4_3_1","volume-title":"HandBook of Mathematical Functions with Formulas, Graphs and Mathematical Tables","author":"Abramowitz M.","year":"1964","unstructured":"M. Abramowitz and I.A. Stegun, HandBook of Mathematical Functions with Formulas, Graphs and Mathematical Tables, Vol.\u00a055.\u00a0US Government Printing Office, Washington, DC, 1964."},{"key":"e_1_3_4_4_1","unstructured":"A. Agarwal S. Negahban and M.J. Wainwright Stochastic optimization and sparse statistical recovery: Optimal algorithms for high dimensions in Advances in Neural Information Processing Systems Vol. 25 F. Pereira C. J. C. Burges L. Bottou and K. Q. Weinberger eds. Curran Associates Inc. Red Hook NY 2012."},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-011-9968-2"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.02.007"},{"key":"e_1_3_4_7_1","unstructured":"D. Alistarh Z. Allen-Zhu and J. Li Byzantine stochastic gradient descent in Advances in Neural Information Processing Systems 31 Curran Associates Inc. Red Hook NY 2018."},{"key":"e_1_3_4_8_1","unstructured":"N.S. Aybat A. Fallah M. G\u00fcrb\u00fczbalaban and A. Ozdaglar A universally optimal multistage accelerated stochastic gradient method in Advances in Neural Information Processing Systems 32 Curran Associates Inc. Red Hook NY 2019."},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1244925"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"key":"e_1_3_4_11_1","unstructured":"J. Bernstein Y. Wang K. Azizzadenesheli and A. Anandkumar signSGD: Compressed optimisation for non-convex problems in Proceedings of the 35th International Conference on Machine Learning Stockhold Sweden volume 80 of Proceedings of Machine Learning Research J. Dy and A. Krause eds. PMLR Brooklyn NY 2018 pp. 560\u2013569."},{"key":"e_1_3_4_12_1","unstructured":"J. Bernstein J. Zhao K. Azizzadenesheli and A. Anandkumar signSGD with majority vote is communication efficient and fault tolerant in International Conference on Learning Representations New Orleans Louisiana USA PMLR 2019."},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3792520"},{"key":"e_1_3_4_15_1","unstructured":"B. Can and M. G\u00fcrb\u00fczbalaban Entropic risk-averse generalized momentum methods preprint (2022). Available at arXiv arXiv:2204.11292."},{"key":"e_1_3_4_16_1","unstructured":"B. Can M. G\u00fcrb\u00fczbalaban and L. Zhu Accelerated linear convergence of stochastic momentum methods in Wasserstein distances in Proceedings of the 36th International Conference on Machine Learning volume 97 of Proceedings of Machine Learning Research Long Beach CA USA K. Chaudhuri and R. Salakhutdinov eds. PMLR Brooklyn NY 2019 pp. 891\u2013901."},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/060676386"},{"key":"e_1_3_4_18_1","unstructured":"O. Devolder Exactness inexactness and stochasticity in first-order methods for large-scale convex optimization Ph.D. thesis ICTEAM and CORE Universit\u00e9 Catholique de Louvain 2013."},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0677-5"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1850"},{"key":"e_1_3_4_21_1","unstructured":"A. Fallah M. G\u00fcrb\u00fczbalaban A. Ozdaglar U. Simsekli and L. Zhu Robust distributed accelerated stochastic gradient methods for multi-agent networks preprint (2019). Available at arXiv arXiv:1910.08701."},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/17M1136845"},{"key":"e_1_3_4_23_1","unstructured":"N. Flammarion and F. Bach From averaging to acceleration there is only a step-size in Proceedings of The 28th Conference on Learning Theory volume 40 of Proceedings of Machine Learning Research Paris France P. Gr\u00fcnwald E. Hazan and S. Kale eds. PMLR Brooklyn NY 2015 pp. 658\u2013695."},{"key":"e_1_3_4_24_1","volume-title":"Controlled Markov Processes and Viscosity Solutions","author":"Fleming W.H.","year":"2006","unstructured":"W.H. Fleming and H.M. Soner, Controlled Markov Processes and Viscosity Solutions, Vol.\u00a025. Springer, New York, NY, 2006."},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1214\/18-EJS1395"},{"key":"e_1_3_4_26_1","unstructured":"A. Ganesh A. Thakurta and J. Upadhyay Langevin diffusion: An almost universal algorithm for private Euclidean (convex) optimization preprint (2022). Available at arXiv arXiv:2204.01585."},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-021-01665-8"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1137\/110848864"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1137\/110848876"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7330562"},{"key":"e_1_3_4_31_1","unstructured":"I. Gitman H. Lang P. Zhang and L. Xiao Understanding the role of momentum in stochastic gradient methods in Advances in Neural Information Processing Systems 32 Curran Associates Inc Red Hook NY 2019."},{"key":"e_1_3_4_32_1","unstructured":"M. Hardt Robustness versus acceleration blog post on Moody Rd August 18 2014. Available at https:\/\/2.zoppoz.workers.dev:443\/http\/blog.mrtz.org\/2014\/08\/18\/robustness-versus-acceleration.html."},{"key":"e_1_3_4_33_1","unstructured":"N.J.A. Harvey C. Liaw Y. Plan and S. Randhawa Tight analyses for non-smooth stochastic gradient descent in Proceedings of the Thirty-Second Conference on Learning Theory volume 99 of Proceedings of Machine Learning Research Phoenix AR USA A. Beygelzimer and D. Hsu eds. PMLR Brooklyn NY 2019 pp. 1579\u20131613."},{"key":"e_1_3_4_34_1","unstructured":"B. Hu and L. Lessard Dissipativity theory for Nesterov's accelerated method in Proceedings of the 34th International Conference on Machine Learning Sydney Australia volume 70 of Proceedings of Machine Learning Research D. Precup and Y.W. Teh eds. PMLR Brooklyn NY 2017 pp. 1549\u20131557."},{"key":"e_1_3_4_35_1","doi-asserted-by":"crossref","unstructured":"B. Hu P. Seiler and L. Lessard Analysis of biased stochastic gradient descent using sequential semidefinite programs Math. Program. 187(1) (2020) pp. 384\u2013408.","DOI":"10.1007\/s10107-020-01486-1"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M128908X"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1355847"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0434-y"},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1009597"},{"key":"e_1_3_4_40_1","unstructured":"X. Li and F. Orabona A high probability analysis of adaptive SGD with momentum preprint (2020). Available at arXiv e-prints arXiv:2007.14294."},{"key":"e_1_3_4_41_1","first-page":"18261","article-title":"An improved analysis of stochastic gradient descent with momentum","volume":"33","author":"Liu Y.","year":"2020","unstructured":"Y. Liu, Y. Gao, and W. Yin, An improved analysis of stochastic gradient descent with momentum, Adv. Neural Inf. Process. Syst. 33 (2020), pp. 18261\u201318271.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_4_42_1","unstructured":"N. Loizou and P. Richt\u00e1rik Momentum and stochastic momentum for stochastic gradient Newton proximal point and subspace descent methods preprint (2017). Available at arXiv e-prints arXiv:1712.09677."},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039796"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2020.1745286"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619183"},{"key":"e_1_3_4_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3008297"},{"key":"e_1_3_4_47_1","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","author":"Nesterov Y.","year":"2003","unstructured":"Y. Nesterov, Introductory Lectures on Convex Optimization: A Basic Course, Vol. 87, Springer, New York, NY, 2003."},{"key":"#cr-split#-e_1_3_4_48_1.1","unstructured":"A. Panigrahi R. Somani N. Goyal and P. Netrapalli Non-gaussianity of stochastic gradient noise NeurIPS SEDL Workshop 2019"},{"key":"#cr-split#-e_1_3_4_48_1.2","unstructured":"arXiv preprint arXiv:1910.09626 (2019)."},{"key":"e_1_3_4_49_1","unstructured":"B.T. Polyak Introduction to optimization in Optimization Software Vol. 1 Inc. Publications Division New York 1987 p. 32."},{"key":"e_1_3_4_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2004.03.004"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2013.0110"},{"key":"e_1_3_4_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/1-84628-095-8_4"},{"key":"e_1_3_4_54_1","unstructured":"M. Schmidt N.L. Roux and F.R. Bach Convergence rates of inexact proximal-gradient methods for convex optimization in Adv. in Neural Inf. Processing Systems 24 J. Shawe-Taylor R.S. Zemel P.L. Bartlett F. Pereira and K.Q. Weinberger eds. Curran Associates Inc. Red Hook NY 2011 pp. 1458\u20131466."},{"key":"e_1_3_4_55_1","unstructured":"B.V. Scoy and L. Lessard The speed-robustness trade-off for first-order methods with additive gradient noise preprint (2021). Available at arXiv arXiv:2109.05059."},{"key":"e_1_3_4_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2017.2722406"},{"key":"e_1_3_4_57_1","unstructured":"O. Sebbouh R.M. Gower and A. Defazio Almost sure convergence rates for stochastic gradient descent and stochastic heavy ball in Proceedings of Thirty Fourth Conference on Learning Theory volume 134 of Proceedings of Machine Learning Research M. Belkin and S. Kpotufe eds. PMLR Brooklyn NY 2021 pp. 3935\u20133971."},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0219024921500199"},{"key":"e_1_3_4_59_1","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"e_1_3_4_60_1","unstructured":"T. Yang Q. Lin and Z. Li Unified convergence analysis of stochastic momentum methods for convex and non-convex optimization preprint (2016). Available at arXiv arXiv:1604.03257."},{"key":"e_1_3_4_61_1","unstructured":"X. Zhang N.S. Aybat and M. G\u00fcrb\u00fczbalaban Robust accelerated primal\u2013dual methods for computing saddle points preprint (2021). Available at arXiv arXiv:2111.12743."}],"container-title":["Optimization Methods and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.tandfonline.com\/doi\/pdf\/10.1080\/10556788.2025.2549356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T13:13:03Z","timestamp":1772716383000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.tandfonline.com\/doi\/full\/10.1080\/10556788.2025.2549356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,2]]},"references-count":61,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,2]]}},"alternative-id":["10.1080\/10556788.2025.2549356"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1080\/10556788.2025.2549356","relation":{},"ISSN":["1055-6788","1029-4937"],"issn-type":[{"value":"1055-6788","type":"print"},{"value":"1029-4937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,2]]},"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":"https:\/\/2.zoppoz.workers.dev:443\/http\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=goms20","URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=goms20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-12-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}