{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T17:29:57Z","timestamp":1784395797894,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Math. Program."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10107-022-01850-3","type":"journal-article","created":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:07:07Z","timestamp":1656601627000},"page":"793-830","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Unifying mirror descent and dual averaging"],"prefix":"10.1007","volume":"199","author":[{"given":"Anatoli","family":"Juditsky","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3464-9081","authenticated-orcid":false,"given":"Joon","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c9ric","family":"Moulines","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,30]]},"reference":[{"key":"1850_CR1","unstructured":"Audibert, J.Y., Bubeck, S.: Minimax policies for adversarial and stochastic bandits. In: Proceedings of the 22nd Annual Conference on Learning Theory (COLT), pp. 217\u2013226 (2009)"},{"key":"1850_CR2","first-page":"2785","volume":"11","author":"JY Audibert","year":"2010","unstructured":"Audibert, J.Y., Bubeck, S.: Regret bounds and minimax policies under partial monitoring. J. Mac. Learn. Res. 11, 2785\u20132836 (2010)","journal-title":"J. Mac. Learn. Res."},{"issue":"1","key":"1850_CR3","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1287\/moor.2013.0598","volume":"39","author":"JY Audibert","year":"2013","unstructured":"Audibert, J.Y., Bubeck, S., Lugosi, G.: Regret in online combinatorial optimization. Math. Oper. Res. 39(1), 31\u201345 (2013)","journal-title":"Math. Oper. Res."},{"issue":"3","key":"1850_CR4","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/S0167-6377(02)00231-6","volume":"31","author":"A Beck","year":"2003","unstructured":"Beck, A., Teboulle, M.: Mirror descent and nonlinear projected subgradient methods for convex optimization. Oper. Res. Lett. 31(3), 167\u2013175 (2003)","journal-title":"Oper. Res. Lett."},{"issue":"1","key":"1850_CR5","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1137\/080716542","volume":"2","author":"A Beck","year":"2009","unstructured":"Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imag. Sci. 2(1), 183\u2013202 (2009)","journal-title":"SIAM J. Imag. Sci."},{"issue":"3","key":"1850_CR6","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/0041-5553(67)90040-7","volume":"7","author":"LM Bregman","year":"1967","unstructured":"Bregman, L.M.: The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Comput. Math. Math. Phys. 7(3), 200\u2013217 (1967)","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"1850_CR7","volume-title":"Introduction To Online Optimization: Lecture Notes","author":"S Bubeck","year":"2011","unstructured":"Bubeck, S.: Introduction To Online Optimization: Lecture Notes. Princeton University, Princeton, NJ (2011)"},{"issue":"3\u20134","key":"1850_CR8","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1561\/2200000050","volume":"8","author":"S Bubeck","year":"2015","unstructured":"Bubeck, S.: Convex optimization: Algorithms and complexity. Foundations and Trends in Machine Learning 8(3\u20134), 231\u2013357 (2015)","journal-title":"Foundations and Trends in Machine Learning"},{"issue":"1","key":"1850_CR9","first-page":"1","volume":"5","author":"S Bubeck","year":"2012","unstructured":"Bubeck, S., Cesa-Bianchi, N.: Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Mach. Learn. 5(1), 1\u2013122 (2012)","journal-title":"Mach. Learn."},{"key":"1850_CR10","unstructured":"Bubeck, S., Cesa-Bianchi, N., Kakade, S.M.: Towards minimax policies for online linear optimization with bandit feedback. In: JMLR: Workshop and Conference Proceedings (COLT), vol.\u00a023, pp. 41.1\u201341.14 (2012)"},{"key":"1850_CR11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921","volume-title":"Prediction, Learning, and Games","author":"N Cesa-Bianchi","year":"2006","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006)"},{"issue":"3","key":"1850_CR12","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1137\/0803026","volume":"3","author":"G Chen","year":"1993","unstructured":"Chen, G., Teboulle, M.: Convergence analysis of a proximal-like minimization algorithm using Bregman functions. SIAM J. Optim. 3(3), 538\u2013543 (1993)","journal-title":"SIAM J. Optim."},{"key":"1850_CR13","unstructured":"Cohen, A., Hazan, T., Koren, T.: Tight bounds for bandit combinatorial optimization. In: Proceedings of Machine Learning Research (COLT 2017) vol. 65, pp. 1\u201314. (2017)"},{"issue":"1\u20132","key":"1850_CR14","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s10107-013-0725-1","volume":"148","author":"B Cox","year":"2014","unstructured":"Cox, B., Juditsky, A., Nemirovski, A.: Dual subgradient algorithms for large-scale nonsmooth learning problems. Math. Program. 148(1\u20132), 143\u2013180 (2014)","journal-title":"Math. Program."},{"key":"1850_CR15","unstructured":"Dasgupta, S., Telgarsky, M.J.: Agglomerative Bregman clustering. In: Proceedings of the 29th International Conference on Machine Learning (ICML 12), pp. 1527\u20131534 (2012)"},{"issue":"Jan","key":"1850_CR16","first-page":"165","volume":"13","author":"O Dekel","year":"2012","unstructured":"Dekel, O., Gilad-Bachrach, R., Shamir, O., Xiao, L.: Optimal distributed online prediction using mini-batches. J. Mach. Learn. Res. 13(Jan), 165\u2013202 (2012)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"1850_CR17","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1109\/TAC.2011.2161027","volume":"57","author":"JC Duchi","year":"2012","unstructured":"Duchi, J.C., Agarwal, A., Wainwright, M.J.: Dual averaging for distributed optimization: Convergence analysis and network scaling. IEEE Trans. Autom. Control. 57(3), 592\u2013606 (2012)","journal-title":"IEEE Trans. Autom. Control."},{"key":"1850_CR18","unstructured":"Duchi, J.C., Ruan, F.: Asymptotic optimality in stochastic optimization. The Annals of Statistics (to appear)"},{"key":"1850_CR19","unstructured":"Flammarion, N., Bach, F.: Stochastic composite least-squares regression with convergence rate O(1\/n). In: Proceedings of Machine Learning Research (COLT 2017), vol. 65, pp. 1\u201344 (2017)"},{"key":"1850_CR20","doi-asserted-by":"crossref","unstructured":"Hazan, E.: The convex optimization approach to regret minimization. In: S.N. S.\u00a0Sra, S.\u00a0Wrigh (eds.) Optimization for Machine Learning, pp. 287\u2013303. MIT press (2012)","DOI":"10.7551\/mitpress\/8996.003.0012"},{"issue":"9","key":"1850_CR21","doi-asserted-by":"crossref","first-page":"149","DOI":"10.7551\/mitpress\/8996.003.0008","volume":"30","author":"A Juditsky","year":"2011","unstructured":"Juditsky, A., Nemirovski, A.: First order methods for nonsmooth convex large-scale optimization, II: utilizing problems structure. Optimization for Machine Learning 30(9), 149\u2013183 (2011)","journal-title":"Optimization for Machine Learning"},{"issue":"5","key":"1850_CR22","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1214\/07-AOS546","volume":"36","author":"A Juditsky","year":"2008","unstructured":"Juditsky, A., Rigollet, P., Tsybakov, A.B.: Learning by mirror averaging. Ann. Stat. 36(5), 2183\u20132206 (2008)","journal-title":"Ann. Stat."},{"issue":"4","key":"1850_CR23","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/s11122-006-0005-2","volume":"41","author":"AB Juditsky","year":"2005","unstructured":"Juditsky, A.B., Nazin, A.V., Tsybakov, A.B., Vayatis, N.: Recursive aggregation of estimators by the mirror descent algorithm with averaging. Probl. Inf. Transm. 41(4), 368\u2013384 (2005)","journal-title":"Probl. Inf. Transm."},{"issue":"1","key":"1850_CR24","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10107-010-0434-y","volume":"133","author":"G Lan","year":"2012","unstructured":"Lan, G.: An optimal method for stochastic composite optimization. Math. Program. 133(1), 365\u2013397 (2012)","journal-title":"Math. Program."},{"issue":"Jun","key":"1850_CR25","first-page":"1705","volume":"13","author":"S Lee","year":"2012","unstructured":"Lee, S., Wright, S.J.: Manifold identification in dual averaging for regularized stochastic online learning. J. Mach. Learn. Res. 13(Jun), 1705\u20131744 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"1850_CR26","unstructured":"McMahan, B.: Follow-the-regularized-leader and mirror descent: Equivalence theorems and l1 regularization. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 525\u2013533 (2011)"},{"issue":"1","key":"1850_CR27","first-page":"3117","volume":"18","author":"HB McMahan","year":"2017","unstructured":"McMahan, H.B.: A survey of algorithms and analysis for adaptive online learning. J. Mac. Learn. Res. 18(1), 3117\u20133166 (2017)","journal-title":"J. Mac. Learn. Res."},{"issue":"1","key":"1850_CR28","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1134\/S0005117918010071","volume":"79","author":"AV Nazin","year":"2018","unstructured":"Nazin, A.V.: Algorithms of inertial mirror descent in convex problems of stochastic optimization. Autom. Remote. Control. 79(1), 78\u201388 (2018)","journal-title":"Autom. Remote. Control."},{"key":"1850_CR29","unstructured":"Nemirovski, A.: Efficient methods for large-scale convex optimization problems. Ekonomika i Matematicheskie Metody 15 (1979)"},{"issue":"1","key":"1850_CR30","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1137\/S1052623403425629","volume":"15","author":"A Nemirovski","year":"2004","unstructured":"Nemirovski, A.: Prox-method with rate of convergence O(1\/t) for variational inequalities with Lipschitz continuous monotone operators and smooth convex-concave saddle point problems. SIAM J. Optim. 15(1), 229\u2013251 (2004)","journal-title":"SIAM J. Optim."},{"issue":"4","key":"1850_CR31","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1137\/070704277","volume":"19","author":"A Nemirovski","year":"2009","unstructured":"Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4), 1574\u20131609 (2009)","journal-title":"SIAM J. Optim."},{"key":"1850_CR32","volume-title":"Problem Complexity and Method Efficiency in Optimization","author":"A Nemirovski","year":"1983","unstructured":"Nemirovski, A., Yudin, D.B.: Problem Complexity and Method Efficiency in Optimization. Wiley Interscience, UK (1983)"},{"issue":"1","key":"1850_CR33","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s10107-004-0552-5","volume":"103","author":"Y Nesterov","year":"2005","unstructured":"Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. 103(1), 127\u2013152 (2005)","journal-title":"Math. Program."},{"issue":"2\u20133","key":"1850_CR34","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s10107-006-0034-z","volume":"109","author":"Y Nesterov","year":"2007","unstructured":"Nesterov, Y.: Dual extrapolation and its applications to solving variational inequalities and related problems. Math. Program. 109(2\u20133), 319\u2013344 (2007)","journal-title":"Math. Program."},{"issue":"1","key":"1850_CR35","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10107-007-0149-x","volume":"120","author":"Y Nesterov","year":"2009","unstructured":"Nesterov, Y.: Primal-dual subgradient methods for convex problems. Math. Program. 120(1), 221\u2013259 (2009)","journal-title":"Math. Program."},{"issue":"3","key":"1850_CR36","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10957-014-0677-5","volume":"165","author":"Y Nesterov","year":"2015","unstructured":"Nesterov, Y., Shikhman, V.: Quasi-monotone subgradient methods for nonsmooth convex minimization. J. Optim. Theory Appl. 165(3), 917\u2013940 (2015)","journal-title":"J. Optim. Theory Appl."},{"key":"1850_CR37","unstructured":"Rakhlin, A., Tewari, A.: Lecture notes on online learning (2009)"},{"key":"1850_CR38","doi-asserted-by":"publisher","DOI":"10.1515\/9781400873173","volume-title":"Convex Analysis","author":"RT Rockafellar","year":"1970","unstructured":"Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton, NJ (1970)"},{"key":"1850_CR39","volume-title":"Online learning: Theory, algorithms, and applications","author":"S Shalev-Shwartz","year":"2007","unstructured":"Shalev-Shwartz, S.: Online learning: Theory, algorithms, and applications. Ph.D. thesis, The Hebrew University of Jerusalem, Israel (2007)"},{"issue":"2","key":"1850_CR40","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1561\/2200000018","volume":"4","author":"S Shalev-Shwartz","year":"2011","unstructured":"Shalev-Shwartz, S.: Online learning and online convex optimization. Foundations and Trends in Machine Learning 4(2), 107\u2013194 (2011)","journal-title":"Foundations and Trends in Machine Learning"},{"key":"1850_CR41","unstructured":"Zinkevich, M.: Online convex programming and generalized infinitesimal gradient ascent. In: Proceedings of the Twentieth International Conference on Machine Learning (ICML) (2003)"}],"container-title":["Mathematical Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10107-022-01850-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10107-022-01850-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10107-022-01850-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T23:46:26Z","timestamp":1700783186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10107-022-01850-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":41,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["1850"],"URL":"https:\/\/doi.org\/10.1007\/s10107-022-01850-3","relation":{},"ISSN":["0025-5610","1436-4646"],"issn-type":[{"value":"0025-5610","type":"print"},{"value":"1436-4646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]},"assertion":[{"value":"30 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}