{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:29:17Z","timestamp":1790756957433,"version":"4.1.0"},"reference-count":53,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-GAGA-13-JS01-0004-01"],"award-info":[{"award-number":["ANR-GAGA-13-JS01-0004-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Optim."],"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:p>In view of solving convex optimization problems with noisy gradient input, we analyze the asymptotic behavior of gradient-like flows under stochastic disturbances. Specifically, we focus on the widely studied class of mirror descent schemes for convex programs with compact feasible regions, and we examine the dynamics' convergence and concentration properties in the presence of noise. In the vanishing noise limit, we show that the dynamics converge to the solution set of the underlying problem (a.s.). Otherwise, when the noise is persistent, we show that the dynamics are concentrated around interior solutions in the long run, and they converge to boundary solutions that are sufficiently \u201csharp.\u201d Finally, we show that a suitably rectified variant of the method converges irrespective of the magnitude of the noise (or the structure of the underlying convex program), and we derive an explicit estimate for its rate of convergence.<\/jats:p>","DOI":"10.1137\/16m1105682","type":"journal-article","created":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T12:18:07Z","timestamp":1516277887000},"page":"163-197","source":"Crossref","is-referenced-by-count":35,"title":["On the Convergence of Gradient-Like Flows with Noisy Gradient Input"],"prefix":"10.1137","volume":"28","author":[{"given":"Panayotis","family":"Mertikopoulos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Staudigl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2018,1,18]]},"reference":[{"key":"atypb1","doi-asserted-by":"publisher","DOI":"10.1080\/02331934.2014.971412"},{"key":"atypb2","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-7824(01)01253-3"},{"key":"atypb3","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012902419977"},{"key":"atypb4","doi-asserted-by":"publisher","DOI":"10.1080\/02331930412331327184"},{"key":"atypb5","doi-asserted-by":"publisher","DOI":"10.1142\/S0219199700000025"},{"key":"atypb6","unstructured":"M. Beckmann, C. B. McGuire, and C. Winsten,\n                      Studies in the Economics of Transportation\n                      , Yale University Press, New Haven, CT, 1956."},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jde.2015.04.016"},{"key":"atypb8","first-page":"1","author":"Benai\u0308m M.","year":"1999","journal-title":"Berlin"},{"key":"atypb9","doi-asserted-by":"publisher","DOI":"10.1007\/BF02218617"},{"key":"atypb10","unstructured":"D. P. Bertsekas and R. Gallager,\n                      Data Networks\n                      , 2nd., Prentice-Hall, Englewood Cliffs, NJ, 1992."},{"key":"atypb11","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176995476"},{"key":"atypb12","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-016-0978-y"},{"key":"atypb13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmaa.2015.11.032"},{"key":"atypb14","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012902410861"},{"key":"atypb15","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2016.06.004"},{"key":"atypb16","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-09-04785-0"},{"key":"atypb17","doi-asserted-by":"publisher","DOI":"10.1137\/0803026"},{"key":"atypb18","doi-asserted-by":"publisher","DOI":"10.1137\/110836043"},{"key":"atypb19","doi-asserted-by":"publisher","DOI":"10.1214\/12-AIHP536"},{"key":"atypb20","doi-asserted-by":"crossref","unstructured":"U. Helmke and J. B. Moore,\n                      Optimization and Dynamical Systems\n                      , Springer, Berlin, 1996.","DOI":"10.1109\/JPROC.1996.503147"},{"key":"atypb21","doi-asserted-by":"crossref","unstructured":"J.B. Hiriart-Urruty and C. Lemare\u0301chal,\n                      Fundamentals of Convex Analysis\n                      , Springer, Berlin, 2001.","DOI":"10.1007\/978-3-642-56468-0"},{"key":"atypb22","doi-asserted-by":"crossref","unstructured":"J. Hofbauer and K. Sigmund,\n                      Evolutionary Games and Population Dynamics\n                      , Cambridge University Press, Cambridge, 1998.","DOI":"10.1017\/CBO9781139173179"},{"key":"atypb23","doi-asserted-by":"publisher","DOI":"10.1214\/105051604000000837"},{"key":"atypb24","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012995290744"},{"key":"atypb25","first-page":"1865","volume":"13","author":"Kakade S. M.","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"atypb26","doi-asserted-by":"crossref","unstructured":"I. Karatzas and S. E. Shreve,\n                      Brownian Motion and Stochastic Calculus\n                      , Springer, Berlin, 1998.","DOI":"10.1007\/978-1-4612-0949-2"},{"key":"atypb27","doi-asserted-by":"crossref","unstructured":"N. Karmarkar,\n                      Riemannian geometry underlying interior point methods for linear programming\n                      , in Mathematical Developments Arising from Linear Programming, Contemp. Math. 114, AMS, Providence, RI, 1990.","DOI":"10.1090\/conm\/114\/1097865"},{"key":"atypb28","doi-asserted-by":"crossref","unstructured":"R. Z. Khasminskii,\n                      Stochastic Stability of Differential Equations\n                      , Stoch. Model. Appl. Probab. 66, 2nd ed., Springer, Berlin, 2012.","DOI":"10.1007\/978-3-642-23280-0"},{"key":"atypb29","doi-asserted-by":"publisher","DOI":"10.1287\/moor.22.2.326"},{"key":"atypb30","doi-asserted-by":"crossref","unstructured":"P. E. Kloeden and E. Platen,\n                      Numerical Solution of Stochastic Differential Equations\n                      , Springer, Berlin, 1992.","DOI":"10.1007\/978-3-662-12616-5"},{"key":"atypb31","unstructured":"W. Krichene,\n                      Continuous and Discrete Dynamics for Online Learning and Convex Optimization\n                      , Ph.D. thesis, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, 2016."},{"key":"atypb32","unstructured":"W. Krichene, A. Bayen, and P. Bartlett,\n                      Accelerated mirror descent in continuous and discrete time\n                      , in Proceedings of the 29th International Conference on Neural Information Processing Systems, 2015."},{"key":"atypb33","doi-asserted-by":"publisher","DOI":"10.3934\/jdg.2017008"},{"key":"atypb34","unstructured":"Q. Li, C. Tai, and W. E,\n                      Dynamics of Stochastic Gradient Algorithms\n                      ,https:\/\/arxiv.org\/abs\/1511.06251, 2015."},{"key":"atypb36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2656847"},{"key":"atypb37","doi-asserted-by":"publisher","DOI":"10.1214\/09-AAP651"},{"key":"atypb38","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0778"},{"key":"atypb39","doi-asserted-by":"publisher","DOI":"10.1007\/s00182-015-0505-7"},{"key":"atypb40","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"atypb41","unstructured":"A. S. Nemirovski and D. B. Yudin,\n                      Problem Complexity and Method Efficiency in Optimization\n                      , Wiley, New York, 1983."},{"key":"atypb42","doi-asserted-by":"crossref","unstructured":"Y. Nesterov,\n                      Introductory Lectures on Convex Optimization: A Basic Course\n                      , Appl. Optim. 87, Kluwer Academic Publishers, Norwell, MA, 2004.","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"atypb43","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0149-x"},{"key":"atypb44","doi-asserted-by":"crossref","unstructured":"E. Pardoux and A. Rascanu,\n                      Stochastic Differential Equations, Backwards SDE, Partial Differential Equations\n                      , Stoch. Model. Appl. Probab., Springer, Berlin, 2014.","DOI":"10.1007\/978-3-319-05714-9"},{"key":"atypb45","unstructured":"B. T. Polyak,\n                      Introduction to Optimization\n                      , Optim. Softw., 1987."},{"key":"atypb46","doi-asserted-by":"crossref","unstructured":"M. Raginsky and J. Bouvrie,\n                      Continuous-time stochastic mirror descent on a network: Variance reduction, consensus, convergence\n                      , in Proceedings of the 51st IEEE Annual Conference on Decision and Control, 2013.","DOI":"10.1109\/CDC.2012.6426639"},{"key":"atypb47","unstructured":"C. Robinson,\n                      Dynamical Systems: Stability, Symbolic Dynamics, and Chaos\n                      , CRC Press, Boca Raton, FL, 1995."},{"key":"atypb48","unstructured":"R. T. Rockafellar,\n                      Convex Analysis\n                      , Princeton University Press, Princeton, NJ, 1970."},{"key":"atypb49","doi-asserted-by":"crossref","unstructured":"R. T. Rockafellar and R. J. B. Wets,\n                      Variational Analysis\n                      , Ser. Comprehensive Stud. Math. 317, Springer, Berlin, 1998.","DOI":"10.1007\/978-3-642-02431-3"},{"key":"atypb50","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"atypb51","doi-asserted-by":"crossref","unstructured":"S. Sra, S. Nowozin, and S. J. Wright,\n                      Optimization for Machine Learning\n                      , MIT Press, Cambridge, MA, 2012.","DOI":"10.7551\/mitpress\/8996.001.0001"},{"key":"atypb52","unstructured":"W. Su, S. Boyd, and E. J. Cande\u0300s,\n                      A differential equation for modeling Nesterov's accelerated gradient method: Theory and insights\n                      , in Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, pp. 2510-2518."},{"key":"atypb53","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.74.197"},{"key":"atypb54","doi-asserted-by":"crossref","unstructured":"A. Wibisono, A. C. Wilson, and M. I. Jordan,\n                      A Variational Perspective on Accelerated Methods in Optimization\n                      ,https:\/\/arxiv.org\/abs\/1603.04245, 2016.","DOI":"10.1073\/pnas.1614734113"}],"container-title":["SIAM Journal on Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/16M1105682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T18:15:00Z","timestamp":1787336100000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/16M1105682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["10.1137\/16M1105682"],"URL":"https:\/\/doi.org\/10.1137\/16m1105682","relation":{},"ISSN":["1052-6234","1095-7189"],"issn-type":[{"value":"1052-6234","type":"print"},{"value":"1095-7189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}