{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:21:40Z","timestamp":1787314900803,"version":"build-2736575974"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC 12171051"],"award-info":[{"award-number":["NSFC 12171051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No. 2023ZCJH02"],"award-info":[{"award-number":["No. 2023ZCJH02"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No. 2025JCTP07"],"award-info":[{"award-number":["No. 2025JCTP07"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s10957-025-02867-2","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:03:33Z","timestamp":1761559413000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Cyclic Stochastic Gradient Descent Method"],"prefix":"10.1007","volume":"208","author":[{"given":"Zhijie","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5660-8280","authenticated-orcid":false,"given":"Cong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"issue":"1","key":"2867_CR1","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1016\/j.apm.2011.07.021","volume":"36","author":"M Ahookhosh","year":"2012","unstructured":"Ahookhosh, M., Amini, K., Peyghami, M.R.: A nonmonotone trust-region line search method for large-scale unconstrained optimization. Appl. Math. Model. 36(1), 478\u2013487 (2012)","journal-title":"Appl. Math. Model."},{"issue":"1","key":"2867_CR2","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1093\/imanum\/8.1.141","volume":"8","author":"J Barzilai","year":"1988","unstructured":"Barzilai, J., Borwein, J.M.: Two-point step size gradient methods. IMA J. Numer. Anal. 8(1), 141\u2013148 (1988)","journal-title":"IMA J. Numer. Anal."},{"issue":"2","key":"2867_CR3","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."},{"issue":"3","key":"2867_CR4","doi-asserted-by":"publisher","first-page":"1","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 Transactions on Intelligent Systems and Technology (TIST) 2(3), 1\u201327 (2011)","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"2867_CR5","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12(7) (2011)"},{"issue":"2","key":"2867_CR6","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1007\/s11081-023-09836-6","volume":"25","author":"S Fathi Hafshejani","year":"2024","unstructured":"Fathi Hafshejani, S., Gaur, D., Hossain, S., Benkoczi, R.: A fast non-monotone line search for stochastic gradient descent. Optim. Eng. 25(2), 1105\u20131124 (2024)","journal-title":"Optim. Eng."},{"key":"2867_CR7","doi-asserted-by":"crossref","unstructured":"Galli, L., Rauhut, H., Schmidt, M.: Don\u2019t be so monotone: relaxing stochastic line search in over-parameterized models. Advances in Neural Information Processing Systems 36 (2024)","DOI":"10.52202\/075280-1509"},{"issue":"4","key":"2867_CR8","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":"2867_CR9","unstructured":"Gower, R.M., Loizou, N., Qian, X., Sailanbayev, A., Shulgin, E., Richt\u00e1rik, P.: SGD: General analysis and improved rates. In: International Conference on Machine Learning, 5200\u20135209. PMLR (2019)"},{"issue":"4","key":"2867_CR10","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1137\/0723046","volume":"23","author":"L Grippo","year":"1986","unstructured":"Grippo, L., Lampariello, F., Lucidi, S.: A nonmonotone line search technique for Newton\u2019s method. SIAM J. Numer. Anal. 23(4), 707\u2013716 (1986)","journal-title":"SIAM J. Numer. Anal."},{"key":"2867_CR11","doi-asserted-by":"crossref","unstructured":"Karimi, H., Nutini, J., Schmidt, M.: Linear convergence of gradient and proximal-gradient methods under the polyak-\u0142ojasiewicz condition. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2016, Riva del Garda, Italy, September 19-23, 2016, Proceedings, Part I 16, pp. 795\u2013811. Springer (2016)","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"2867_CR12","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR). San Diega, CA, USA (2015)"},{"key":"2867_CR13","unstructured":"Loizou, N., Vaswani, S., Laradji, I.H., Lacoste-Julien, S.: Stochastic polyak step-size for SGD: An adaptive learning rate for fast convergence. International Conference on Artificial Intelligence and Statistics, 1306\u20131314. PMLR (2021)"},{"key":"2867_CR14","unstructured":"Moulines, E., Bach, F.: Non-asymptotic analysis of stochastic approximation algorithms for machine learning. Advances in Neural Information Processing Systems 24 (2011)"},{"key":"2867_CR15","unstructured":"Needell, D., Ward, R., Srebro, N.: Stochastic gradient descent, weighted sampling, and the randomized kaczmarz algorithm. Advances in Neural Information Processing Systems 27 (2014)"},{"issue":"3","key":"2867_CR16","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":"2867_CR17","unstructured":"Smith, S.L., Kindermans, P.J., Ying, C., Le, Q.V.: Don\u2019t decay the learning rate, increase the batch size. In: International Conference on Learning Representations (2018)"},{"key":"2867_CR18","unstructured":"Tan, C., Ma, S., Dai, Y.H., Qian, Y.: Barzilai-Borwein step size for stochastic gradient descent. Advances in Neural Information Processing Systems 29 (2016)"},{"key":"2867_CR19","unstructured":"Tieleman, T., Hinton, G.: Divide the gradient by a running average of its recent magnitude. coursera: Neural networks for machine learning. Technical Report (2017)"},{"key":"2867_CR20","unstructured":"Vaswani, S., Mishkin, A., Laradji, I., Schmidt, M., Gidel, G., Lacoste-Julien, S.: Painless stochastic gradient: Interpolation, line-search, and convergence rates. Advances in Neural Information Processing Systems 32 (2019)"},{"issue":"48","key":"2867_CR21","first-page":"1","volume":"24","author":"X Wang","year":"2023","unstructured":"Wang, X., Yuan, Yx.: On the convergence of stochastic gradient descent with bandwidth-based step size. Journal of Machine Learning Research 24(48), 1\u201349 (2023)","journal-title":"Journal of Machine Learning Research"},{"key":"2867_CR22","unstructured":"Xing, C., Arpit, D., Tsirigotis, C., Bengio, Y.: A walk with SGD. arXiv preprint arXiv:1802.08770 (2018)"},{"key":"2867_CR23","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"issue":"4","key":"2867_CR24","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1137\/S1052623403428208","volume":"14","author":"H Zhang","year":"2004","unstructured":"Zhang, H., Hager, W.W.: A nonmonotone line search technique and its application to unconstrained optimization. SIAM J. Optim. 14(4), 1043\u20131056 (2004)","journal-title":"SIAM J. Optim."},{"issue":"3","key":"2867_CR25","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1007\/s40305-022-00432-6","volume":"12","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Sun, C.: Cyclic gradient methods for unconstrained optimization. Journal of the Operations Research Society of China 12(3), 809\u2013828 (2024)","journal-title":"Journal of the Operations Research Society of China"}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02867-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-025-02867-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02867-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:23:13Z","timestamp":1775028193000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-025-02867-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2867"],"URL":"https:\/\/doi.org\/10.1007\/s10957-025-02867-2","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"29 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"42"}}