{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:45:10Z","timestamp":1740123910800,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100009515","name":"Fondation Simone et Cino Del Duca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009515","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["MASDOL","SCAI Statistics and Computation for AI (chaire IA)"],"award-info":[{"award-number":["MASDOL","SCAI Statistics and Computation for AI (chaire IA)"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Russian Academic Excellence Project","award":["5-100"],"award-info":[{"award-number":["5-100"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11222-021-10023-9","type":"journal-article","created":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T05:02:42Z","timestamp":1623733362000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Fast incremental expectation maximization for finite-sum optimization: nonasymptotic convergence"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5400-1058","authenticated-orcid":false,"given":"G.","family":"Fort","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Gach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Moulines","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,15]]},"reference":[{"key":"10023_CR1","unstructured":"Agarwal, A., Bottou, L.: A lower bound for the optimization of finite sums. In: Bach, F., Blei, D. (eds.), Proceedings of the 32nd International Conference on Machine Learning, PMLR, Proceedings of Machine Learning Research, vol. 37, pp. 78\u201386 (2015)"},{"key":"10023_CR2","unstructured":"Allen-Zhu, Z., Hazan, E.: Variance reduction for faster non-convex optimization. In: Balcan, M., Weinberger, K. (eds.), Proceedings of The 33rd International Conference on Machine Learning, PMLR, Proceedings of Machine Learning Research, vol. 48, pp. 699\u2013707 (2016)"},{"key":"10023_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75894-2","volume-title":"Adaptive Algorithms and Stochastic Approximations","author":"A Benveniste","year":"1990","unstructured":"Benveniste, A., Priouret, P., M\u00e9tivier, M.: Adaptive Algorithms and Stochastic Approximations. Springer, Berlin (1990)"},{"key":"10023_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","author":"V Borkar","year":"2008","unstructured":"Borkar, V.: Stochastic Approximation: A Dynamical Systems Viewpoint. Cambridge University Press, Cambridge (2008)"},{"key":"10023_CR5","first-page":"421","volume-title":"Stochastic Gradient Descent Tricks","author":"L Bottou","year":"2012","unstructured":"Bottou, L.: Stochastic Gradient Descent Tricks, pp. 421\u2013436. Springer, Berlin (2012)"},{"key":"10023_CR6","volume-title":"Fundamentals of Statistical Exponential Families with Applications in Statistical Decision Theory, Institute of Mathematical Statistics Lecture Notes-Monograph Series","author":"LD Brown","year":"1986","unstructured":"Brown, L.D.: Fundamentals of Statistical Exponential Families with Applications in Statistical Decision Theory, Institute of Mathematical Statistics Lecture Notes-Monograph Series, vol. 9. Institute of Mathematical Statistics, Hayward (1986)"},{"issue":"3","key":"10023_CR7","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1111\/j.1467-9868.2009.00698.x","volume":"71","author":"O Capp\u00e9","year":"2009","unstructured":"Capp\u00e9, O., Moulines, E.: On-line Expectation Maximization algorithm for latent data models. J. R. Stat. Soc. B Met. 71(3), 593\u2013613 (2009)","journal-title":"J. R. Stat. Soc. B Met."},{"key":"10023_CR8","first-page":"73","volume":"2","author":"G Celeux","year":"1985","unstructured":"Celeux, G., Diebolt, J.: The SEM algorithm: a probabilistic teacher algorithm derived from the EM algorithm for the mixture problem. Comput. Stat. Q. 2, 73\u201382 (1985)","journal-title":"Comput. Stat. Q."},{"key":"10023_CR9","first-page":"7967","volume-title":"Advances in Neural Information Processing Systems","author":"J Chen","year":"2018","unstructured":"Chen, J., Zhu, J., Teh, Y., Zhang, T.: Stochastic expectation maximization with variance reduction. In: Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R., Bengio, S. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 7967\u20137977. Curran Associates Inc, Red Hook (2018)"},{"key":"10023_CR10","unstructured":"Csisz\u00e1r, I., Tusn\u00e1dy, G.: Information geometry and alternating minimization procedures. In: Recent Results in Estimation Theory and Related Topics, suppl. 1, Statist. Decisions, pp. 205\u2013237 (1984)"},{"key":"10023_CR11","first-page":"1646","volume-title":"Advances in Neural Information Processing Systems","author":"A Defazio","year":"2014","unstructured":"Defazio, A., Bach, F., Lacoste-Julien, S.: SAGA: a fast incremental gradient method with support for non-strongly convex composite objectives. In: Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 1646\u20131654. Curran Associates Inc, Red Hook (2014)"},{"issue":"1","key":"10023_CR12","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1214\/aos\/1018031103","volume":"27","author":"B Delyon","year":"1999","unstructured":"Delyon, B., Lavielle, M., Moulines, E.: Convergence of a Stochastic Approximation version of the EM algorithm. Ann. Stat. 27(1), 94\u2013128 (1999)","journal-title":"Ann. Stat."},{"issue":"1","key":"10023_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. B Met. 39(1), 1\u201338 (1977)","journal-title":"J. R. Stat. Soc. B Met."},{"key":"10023_CR14","first-page":"689","volume-title":"Advances in Neural Information Processing Systems","author":"C Fang","year":"2018","unstructured":"Fang, C., Li, C., Lin, Z., Zhang, T.: SPIDER: near-optimal non-convex optimization via stochastic path-integrated differential estimator. In: Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R., Bengio, S. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 689\u2013699. Curran Associates Inc, Red Hook (2018)"},{"issue":"4","key":"10023_CR15","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1214\/aos\/1059655912","volume":"31","author":"G Fort","year":"2003","unstructured":"Fort, G., Moulines, E.: Convergence of the Monte Carlo Expectation Maximization for curved exponential families. Ann. Stat. 31(4), 1220\u20131259 (2003)","journal-title":"Ann. Stat."},{"volume-title":"Handbook of Mixture Analysis. Handbooks of Modern Statistical Methods","year":"2019","key":"10023_CR16","unstructured":"Fr\u00fchwirth-Schnatter, S., Celeux, G., Robert, C.P. (eds.): Handbook of Mixture Analysis. Handbooks of Modern Statistical Methods. Chapman & Hall\/CRC Press, Boca Raton (2019)"},{"issue":"4","key":"10023_CR17","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1137\/120880811","volume":"23","author":"S Ghadimi","year":"2013","unstructured":"Ghadimi, S., Lan, G.: Stochastic first- and zeroth-order methods for nonconvex stochastic programming. SIAM J. Optim. 23(4), 2341\u20132368 (2013)","journal-title":"SIAM J. Optim."},{"key":"10023_CR18","volume-title":"Monte Carlo Methods in Financial Engineering","author":"P Glasserman","year":"2004","unstructured":"Glasserman, P.: Monte Carlo Methods in Financial Engineering. Springer, New York (2004)"},{"key":"10023_CR19","first-page":"2049","volume":"6","author":"A Gunawardana","year":"2005","unstructured":"Gunawardana, A., Byrne, W.: Convergence theorems for generalized alternating minimization procedures. J. Mach. Learn. Res. 6, 2049\u20132073 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"10023_CR20","first-page":"315","volume-title":"Advances in Neural Information Processing Systems","author":"R Johnson","year":"2013","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q., Burges, C.J.C. (eds.) Advances in Neural Information Processing Systems, vol. 26, pp. 315\u2013323. Curran Associates Inc, Red Hook (2013)"},{"key":"10023_CR21","unstructured":"Karimi, B., Miasojedow, B., Moulines, E., Wai, H.T.: Non-asymptotic analysis of biased stochastic approximation scheme. In: Beygelzimer, A., Hsu, D. (eds.) Proceedings of the Thirty-Second Conference on Learning Theory, PMLR, Phoenix, USA, Proceedings of Machine Learning Research, vol. 99, pp. 1944\u20131974 (2019a)"},{"key":"10023_CR22","first-page":"2837","volume-title":"Advances in Neural Information Processing Systems","author":"B Karimi","year":"2019","unstructured":"Karimi, B., Wai, H.T., Moulines, E., Lavielle, M.: On the global convergence of (fast) incremental expectation maximization methods. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9 Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 2837\u20132847. Curran Associates Inc, Red Hook (2019b)"},{"key":"10023_CR23","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1007\/s10044-014-0441-3","volume":"18","author":"W Kwedlo","year":"2015","unstructured":"Kwedlo, W.: A new random approach for initialization of the multiple restart EM algorithm for Gaussian model-based clustering. Pattern Anal. Appl. 18, 757\u2013770 (2015)","journal-title":"Pattern Anal. Appl."},{"key":"10023_CR24","doi-asserted-by":"crossref","unstructured":"Lange, K.: MM Optimization Algorithms. Other Titles in Applied Mathematics, Society for Industrial and Applied Mathematics (2016)","DOI":"10.1137\/1.9781611974409"},{"issue":"2","key":"10023_CR25","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1111\/j.2517-6161.1995.tb02037.x","volume":"57","author":"K Lange","year":"1995","unstructured":"Lange, K.: A gradient algorithm locally equivalent to the EM algorithm. J. R. Stat. Soc. B 57(2), 425\u2013437 (1995)","journal-title":"J. R. Stat. Soc. B"},{"key":"10023_CR26","volume-title":"Statistical Analysis with Missing Data. Wiley Series in Probability and Statistics","author":"RJA Little","year":"2002","unstructured":"Little, R.J.A., Rubin, D.: Statistical Analysis with Missing Data. Wiley Series in Probability and Statistics, 2nd edn. Wiley, Hoboken (2002)","edition":"2"},{"key":"10023_CR27","volume-title":"The EM Algorithm and Extensions. Wiley Series in Probability and Statistics","author":"G McLachlan","year":"2008","unstructured":"McLachlan, G., Krishnan, T.: The EM Algorithm and Extensions. Wiley Series in Probability and Statistics. Wiley, New York (2008)"},{"key":"10023_CR28","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/BF02592948","volume":"39","author":"K Murty","year":"1987","unstructured":"Murty, K., Kabadi, S.: Some NP-complete problems in quadratic and nonlinear programming. Math. Program. 39, 117\u2013129 (1987)","journal-title":"Math. Program."},{"key":"10023_CR29","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-94-011-5014-9_12","volume-title":"Learning in Graphical Models","author":"RM Neal","year":"1998","unstructured":"Neal, R.M., Hinton, G.E.: A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Jordan, M.I. (ed.) Learning in Graphical Models, pp. 355\u2013368. Springer, Dordrecht (1998)"},{"issue":"1","key":"10023_CR30","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1023\/A:1021987710829","volume":"13","author":"SK Ng","year":"2003","unstructured":"Ng, S.K., McLachlan, G.J.: On the choice of the number of blocks with the incremental EM algorithm for the fitting of normal mixtures. Stat. Comput. 13(1), 45\u201355 (2003)","journal-title":"Stat. Comput."},{"key":"10023_CR31","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1007\/s11222-019-09919-4","volume":"30","author":"H Nguyen","year":"2020","unstructured":"Nguyen, H., Forbes, F., McLachlan, G.: Mini-batch learning of exponential family finite mixture models. Stat. Comput. 30, 731\u2013748 (2020)","journal-title":"Stat. Comput."},{"key":"10023_CR32","unstructured":"Parizi, S.N., He, K., Aghajani, R., Sclaroff, S., Felzenszwalb, P.: Generalized majorization-minimization. In: Proceedings of the 36th International Conference on Machine Learning, PMLR, Long Beach, California, USA, Proceedings of Machine Learning Research, vol. 97, pp. 5022\u20135031 (2019)"},{"key":"10023_CR33","doi-asserted-by":"crossref","unstructured":"Reddi, S., Sra, S., P\u00f3czos, B., Smola, A.: Fast incremental method for smooth nonconvex optimization. In: 2016 IEEE 55th conference on decision and control (CDC), pp. 1971\u20131977 (2016)","DOI":"10.1109\/CDC.2016.7798553"},{"issue":"3","key":"10023_CR34","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22(3), 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"issue":"1\u20132","key":"10023_CR35","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s10107-016-1030-6","volume":"162","author":"M Schmidt","year":"2017","unstructured":"Schmidt, M., Le Roux, N., Bach, F.: Minimizing finite sums with the stochastic average gradient. Math. Program. 162(1\u20132), 83\u2013112 (2017)","journal-title":"Math. Program."},{"key":"10023_CR36","doi-asserted-by":"publisher","DOI":"10.1017\/9781108604574","volume-title":"Statistical Modelling by Exponential Families","author":"R Sundberg","year":"2019","unstructured":"Sundberg, R.: Statistical Modelling by Exponential Families. Cambridge University Press, Cambridge (2019)"},{"issue":"411","key":"10023_CR37","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1080\/01621459.1990.10474930","volume":"85","author":"G Wei","year":"1990","unstructured":"Wei, G., Tanner, M.: A Monte Carlo implementation of the EM algorithm and the poor man\u2019s data augmentation algorithms. J. Am. Stat. Assoc. 85(411), 699\u2013704 (1990)","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"10023_CR38","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1214\/aos\/1176346060","volume":"11","author":"C Wu","year":"1983","unstructured":"Wu, C.: On the convergence properties of the EM algorithm. Ann. Stat. 11(1), 95\u2013103 (1983)","journal-title":"Ann. Stat."},{"key":"10023_CR39","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1287\/mnsc.13.5.344","volume":"13","author":"WI Zangwill","year":"1967","unstructured":"Zangwill, W.I.: Non-linear programming via penalty functions. Manag. Sci. 13, 344\u2013358 (1967)","journal-title":"Manag. Sci."},{"key":"10023_CR40","first-page":"3921","volume-title":"Advances in Neural Information Processing Systems","author":"D Zhou","year":"2018","unstructured":"Zhou, D., Xu, P., Gu, Q.: Stochastic nested variance reduced gradient descent for nonconvex optimization. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 3921\u20133932. Curran Associates Inc, Red Hook (2018)"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-021-10023-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-021-10023-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-021-10023-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T20:31:21Z","timestamp":1725222681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-021-10023-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,15]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["10023"],"URL":"https:\/\/doi.org\/10.1007\/s11222-021-10023-9","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"type":"print","value":"0960-3174"},{"type":"electronic","value":"1573-1375"}],"subject":[],"published":{"date-parts":[[2021,6,15]]},"assertion":[{"value":"23 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"48"}}