{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:58:24Z","timestamp":1768316304997,"version":"3.49.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Optim Appl"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s10589-022-00375-x","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T21:05:48Z","timestamp":1653080748000},"page":"561-593","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Finite-sum smooth optimization with SARAH"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6083-606X","authenticated-orcid":false,"given":"Lam M.","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Marten","family":"van Dijk","sequence":"additional","affiliation":[]},{"given":"Dzung T.","family":"Phan","sequence":"additional","affiliation":[]},{"given":"Phuong Ha","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Tsui-Wei","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Jayant R.","family":"Kalagnanam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,20]]},"reference":[{"key":"375_CR1","unstructured":"Allen-Zhu, Z.: Natasha: faster non-convex stochastic optimization via strongly non-convex parameter. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 89\u201397 (2017)"},{"key":"375_CR2","unstructured":"Allen-Zhu, Z.: Natasha 2: faster non-convex optimization than sgd. In: Advances in Neural Information Processing Systems, pp. 2675\u20132686 (2018)"},{"key":"375_CR3","unstructured":"Allen-Zhu, Z., Yuan, Y.: Improved SVRG for non-strongly-convex or sum-of-non-convex objectives. In: ICML, pp. 1080\u20131089 (2016)"},{"issue":"2","key":"375_CR4","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"key":"375_CR5","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 271\u20132727 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"375_CR6","unstructured":"Defazio, A., Bach, F., Lacoste-Julien, S.: Saga: a fast incremental gradient method with support for non-strongly convex composite objectives. In: Advances in Neural Information Processing Systems, pp. 1646\u20131654 (2014)"},{"key":"375_CR7","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"375_CR8","unstructured":"Fang, C., Li, C.J., Lin, Z., Zhang, T.: Spider: near-optimal non-convex optimization via stochastic path-integrated differential estimator. In: Advances in Neural Information Processing Systems, pp. 689\u2013699 (2018)"},{"key":"375_CR9","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Advances in Neural Information Processing Systems, pp. 315\u2013323 (2013)"},{"key":"375_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR arXiv:1412.6980 (2014)"},{"key":"375_CR11","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3389\/fams.2017.00009","volume":"3","author":"J Kone\u010dn\u1ef3","year":"2017","unstructured":"Kone\u010dn\u1ef3, J., Richt\u00e1rik, P.: Semi-stochastic gradient descent methods. Front. Appl. Math. Stat. 3, 9 (2017)","journal-title":"Front. Appl. Math. Stat."},{"key":"375_CR12","unstructured":"Lei, L., Ju, C., Chen, J., Jordan, M.I.: Non-convex finite-sum optimization via SCSG methods. In:\u00a0Guyon, I., Luxburg, U.V.,\u00a0Bengio, S.,\u00a0Wallach, H.,\u00a0Fergus, R.,\u00a0Vishwanathan, S.,\u00a0Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 2348\u20132358. Curran Associates, Inc. (2017)"},{"key":"375_CR13","unstructured":"Li, Z., Bao, H., Zhang, X., Richt\u00e1rik, P.: Page: a simple and optimal probabilistic gradient estimator for nonconvex optimization. In: International Conference on Machine Learning, pp. 6286\u20136295. PMLR (2021)"},{"key":"375_CR14","unstructured":"Liu, Y., Feng, F., Yin, W.: Acceleration of svrg and katyusha x by inexact preconditioning. In: International Conference on Machine Learning, pp. 4003\u20134012. PMLR (2019)"},{"key":"375_CR15","unstructured":"Mairal, J.: Optimization with first-order surrogate functions. In: International Conference on Machine Learning, pp. 783\u2013791 (2013)"},{"key":"375_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course. Applied Optimization","author":"Y Nesterov","year":"2004","unstructured":"Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course. Applied Optimization. Kluwer Academic Publ, Boston (2004)"},{"key":"375_CR17","unstructured":"Nguyen, L., Nguyen, P.H., van Dijk, M., Richtarik, P., Scheinberg, K., Takac, M.: SGD and Hogwild! Convergence without the bounded gradients assumption. In: Proceedings of the 35th International Conference on Machine Learning, vol. 80, pp. 3747\u20133755 (2018)"},{"key":"375_CR18","unstructured":"Nguyen, L.M., Liu, J., Scheinberg, K., Tak\u00e1\u010d, M.: SARAH: a novel method for machine learning problems using stochastic recursive gradient. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2613\u20132621 (2017)"},{"key":"375_CR19","unstructured":"Nguyen, L.M., Liu, J., Scheinberg, K., Tak\u00e1c, M.: Stochastic recursive gradient algorithm for nonconvex optimization. CoRR arXiv:1705.07261 (2017)"},{"issue":"176","key":"375_CR20","first-page":"1","volume":"20","author":"LM Nguyen","year":"2019","unstructured":"Nguyen, L.M., Nguyen, P.H., Richt\u00e1rik, P., Scheinberg, K., Tak\u00e1\u010d, M., van Dijk, M.: New convergence aspects of stochastic gradient algorithms. J. Mach. Learn. Res. 20(176), 1\u201349 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"375_CR21","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2020.1818081","author":"LM Nguyen","year":"2020","unstructured":"Nguyen, L.M., Scheinberg, K., Takac, M.: Inexact sarah algorithm for stochastic optimization. Optim. Methods Softw. (2020). https:\/\/doi.org\/10.1080\/10556788.2020.1818081","journal-title":"Optim. Methods Softw."},{"key":"375_CR22","first-page":"110","volume":"21","author":"NH Pham","year":"2020","unstructured":"Pham, N.H., Nguyen, L.M., Phan, D.T., Tran-Dinh, Q.: Proxsarah: an efficient algorithmic framework for stochastic composite nonconvex optimization. J. Mach. Learn. Res. 21, 110\u20131 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"375_CR23","doi-asserted-by":"crossref","unstructured":"Reddi, S.J., Hefny, A., Sra, S., Poczos, B., Smola, A.: Stochastic variance reduction for nonconvex optimization. In: International Conference on Machine Learning, pp. 314\u2013323 (2016)","DOI":"10.1109\/ALLERTON.2016.7852377"},{"issue":"3","key":"375_CR24","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."},{"key":"375_CR25","unstructured":"Roux, N.L., Schmidt, M., Bach, F.R.: A stochastic gradient method with an exponential convergence _rate for finite training sets. In: Advances in Neural Information Processing Systems, pp. 2663\u20132671 (2012)"},{"issue":"1","key":"375_CR26","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), 83\u2013112 (2017)","journal-title":"Math. Program."},{"issue":"1","key":"375_CR27","first-page":"567","volume":"14","author":"S Shalev-Shwartz","year":"2013","unstructured":"Shalev-Shwartz, S., Zhang, T.: Stochastic dual coordinate ascent methods for regularized loss. J. Mach. Learn. Res. 14(1), 567\u2013599 (2013)","journal-title":"J. Mach. Learn. Res."},{"key":"375_CR28","unstructured":"Wang, Z., Ji, K., Zhou, Y., Liang, Y., Tarokh, V.: Spiderboost: a class of faster variance-reduced algorithms for nonconvex optimization. In: Advances in Neural Information Processing Systems (2019)"},{"key":"375_CR29","unstructured":"Zhou, D., Xu, P., Gu, Q.: Stochastic nested variance reduced gradient descent for nonconvex optimization. In: Advances in Neural Information Processing Systems, pp. 3921\u20133932 (2018)"}],"container-title":["Computational Optimization and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-022-00375-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10589-022-00375-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-022-00375-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T11:11:29Z","timestamp":1655723489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10589-022-00375-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,20]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["375"],"URL":"https:\/\/doi.org\/10.1007\/s10589-022-00375-x","relation":{},"ISSN":["0926-6003","1573-2894"],"issn-type":[{"value":"0926-6003","type":"print"},{"value":"1573-2894","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,20]]},"assertion":[{"value":"19 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}