{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T12:39:38Z","timestamp":1786451978237,"version":"3.56.0"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007345","name":"King Mongkut's University of Technology North Bangkok","doi-asserted-by":"publisher","award":["KMUTNB-FF-69-A-06"],"award-info":[{"award-number":["KMUTNB-FF-69-A-06"]}],"id":[{"id":"10.13039\/501100007345","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014796","name":"Center of Excellence in Theoretical and Computational Science, King Mongkut's University of Technology Thonburi","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014796","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004705","name":"King Mongkut's University of Technology Thonburi","doi-asserted-by":"publisher","award":["24\/2565"],"award-info":[{"award-number":["24\/2565"]}],"id":[{"id":"10.13039\/501100004705","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational and Applied Mathematics"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.cam.2026.117559","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:53:16Z","timestamp":1772207596000},"page":"117559","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["An adaptive stochastic gradient method with variance reduction for smooth optimization problems"],"prefix":"10.1016","volume":"484","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6915-2630","authenticated-orcid":false,"given":"Mahmoud M.","family":"Yahaya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5463-4581","authenticated-orcid":false,"given":"Poom","family":"Kumam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1240-1181","authenticated-orcid":false,"given":"Thidaporn","family":"Seangwattana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cam.2026.117559_bib0001","series-title":"Statistical Models in S","first-page":"249","article-title":"Generalized additive models","author":"Hastie","year":"2017"},{"key":"10.1016\/j.cam.2026.117559_bib0002","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1011441423217","article-title":"Text categorization based on regularized linear classification methods","volume":"4","author":"Zhang","year":"2001","journal-title":"Inf. Retr. Boston"},{"key":"10.1016\/j.cam.2026.117559_sbref0003","series-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"10.1016\/j.cam.2026.117559_bib0004","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","author":"Robbins","year":"1951","journal-title":"Annal. Math. Stat."},{"key":"10.1016\/j.cam.2026.117559_bib0005","article-title":"The tradeoffs of large scale learning","volume":"20","author":"Bottou","year":"2007","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0006","series-title":"Proceedings of the Twenty-first International Conference on Machine Learning","first-page":"116","article-title":"Solving large scale linear prediction problems using stochastic gradient descent algorithms","author":"Zhang","year":"2004"},{"issue":"9","key":"10.1016\/j.cam.2026.117559_bib0007","first-page":"1269","article-title":"Performance analysis of stochastic gradient algorithms under weak conditions","volume":"51","author":"Ding","year":"2008","journal-title":"Sci. China Ser. F: Inf. Sci."},{"key":"10.1016\/j.cam.2026.117559_bib0008","article-title":"A stochastic gradient method with an exponential convergence _rate for finite training sets","volume":"25","author":"Roux","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7","key":"10.1016\/j.cam.2026.117559_bib0009","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cam.2026.117559_bib0010","unstructured":"M.D. Zeiler, Adadelta: an adaptive learning rate method, (2012). arXiv preprint arXiv: 1212.5701."},{"issue":"2","key":"10.1016\/j.cam.2026.117559_bib0011","first-page":"26","article-title":"Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"10.1016\/j.cam.2026.117559_bib0012","unstructured":"D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, (2014). arXiv preprint arXiv: 1412.6980."},{"key":"10.1016\/j.cam.2026.117559_bib0013","article-title":"The marginal value of adaptive gradient methods in machine learning","volume":"30","author":"Wilson","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0014","article-title":"Better mini-batch algorithms via accelerated gradient methods","volume":"24","author":"Cotter","year":"2011","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0015","series-title":"International Conference on Machine Learning","first-page":"1","article-title":"Stochastic optimization with importance sampling for regularized loss minimization","author":"Zhao","year":"2015"},{"issue":"1","key":"10.1016\/j.cam.2026.117559_bib0016","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.ejor.2019.01.013","article-title":"Importance sampling in stochastic optimization: an application to intertemporal portfolio choice","volume":"285","author":"Ekblom","year":"2020","journal-title":"Eur. J. Oper. Res."},{"issue":"1","key":"10.1016\/j.cam.2026.117559_bib0017","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10915-022-02084-3","article-title":"A line search based proximal stochastic gradient algorithm with dynamical variance reduction","volume":"94","author":"Franchini","year":"2023","journal-title":"J. Sci. Comput."},{"key":"10.1016\/j.cam.2026.117559_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.cam.2024.116083","article-title":"A stochastic gradient method with variance control and variable learning rate for deep learning","volume":"451","author":"Franchini","year":"2024","journal-title":"J. Comput. Appl. Math."},{"key":"10.1016\/j.cam.2026.117559_bib0019","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","volume":"27","author":"Defazio","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0020","series-title":"Proceedings of the 9Th Conference on Winter simulation-Volume 1","first-page":"152","article-title":"The application of control variables to the simulation of closed queueing networks","author":"Lavenberg","year":"1977"},{"key":"10.1016\/j.cam.2026.117559_bib0021","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume":"26","author":"Johnson","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0022","doi-asserted-by":"crossref","first-page":"9","DOI":"10.3389\/fams.2017.00009","article-title":"Semi-stochastic gradient descent methods","volume":"3","author":"Kone\u010dn\u00fd","year":"2017","journal-title":"Front. Appl. Math. Stat."},{"issue":"2","key":"10.1016\/j.cam.2026.117559_bib0023","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/JSTSP.2015.2505682","article-title":"Mini-batch semi-stochastic gradient descent in the proximal setting","volume":"10","author":"Kone\u010dn\u1ef3","year":"2015","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.cam.2026.117559_bib0024","series-title":"International Conference on Machine Learning","first-page":"2613","article-title":"SARAH: A novel method for machine learning problems using stochastic recursive gradient","author":"Nguyen","year":"2017"},{"key":"10.1016\/j.cam.2026.117559_bib0025","unstructured":"L.M. Nguyen, J. Liu, K. Scheinberg, M. Tak\u00e1\u010d, Stochastic recursive gradient algorithm for nonconvex optimization, (2017b). arXiv preprint arXiv: 1705.07261."},{"key":"10.1016\/j.cam.2026.117559_bib0026","article-title":"Spider: near-optimal non-convex optimization via stochastic path-integrated differential estimator","volume":"31","author":"Fang","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0027","article-title":"Spiderboost and momentum: faster variance reduction algorithms","volume":"32","author":"Wang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cam.2026.117559_bib0028","series-title":"Artificial Intelligence and Statistics","first-page":"148","article-title":"Less than a single pass: stochastically controlled stochastic gradient","author":"Lei","year":"2017"},{"key":"10.1016\/j.cam.2026.117559_bib0029","article-title":"Barzilai-borwein step size for stochastic gradient descent","volume":"29","author":"Tan","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.cam.2026.117559_bib0030","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1093\/imanum\/8.1.141","article-title":"Two-point step size gradient methods","volume":"8","author":"Barzilai","year":"1988","journal-title":"IMA J. Numer. Anal."},{"key":"10.1016\/j.cam.2026.117559_bib0031","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.neucom.2018.06.002","article-title":"Mini-batch algorithms with barzilai\u2013Borwein update step","volume":"314","author":"Yang","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cam.2026.117559_bib0032","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.sigpro.2019.02.010","article-title":"Accelerated stochastic gradient descent with step size selection rules","volume":"159","author":"Yang","year":"2019","journal-title":"Signal Process."},{"key":"10.1016\/j.cam.2026.117559_bib0033","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.engappai.2018.03.017","article-title":"Random barzilai\u2013Borwein step size for mini-batch algorithms","volume":"72","author":"Yang","year":"2018","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.cam.2026.117559_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114336","article-title":"On the step size selection in variance-reduced algorithm for nonconvex optimization","volume":"169","author":"Yang","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cam.2026.117559_bib0035","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.patrec.2019.08.029","article-title":"Barzilai\u2013Borwein-based adaptive learning rate for deep learning","volume":"128","author":"Liang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.cam.2026.117559_bib0036","series-title":"Numerical Analysis and Optimization: NAO-III, Muscat, Oman, January 2014","first-page":"59","article-title":"A positive barzilai\u2013Borwein-like stepsize and an extension for symmetric linear systems","author":"Dai","year":"2015"},{"key":"10.1016\/j.cam.2026.117559_bib0037","doi-asserted-by":"crossref","first-page":"916","DOI":"10.4208\/jcm.1911-m2019-0171","article-title":"Stabilized barzilai-borwein method","author":"Burdakov","year":"2019","journal-title":"J. Comput. Math."},{"key":"10.1016\/j.cam.2026.117559_bib0038","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s10589-006-6446-0","article-title":"Gradient methods with adaptive step-sizes","volume":"35","author":"Zhou","year":"2006","journal-title":"Comput. Optim. Appl."},{"key":"10.1016\/j.cam.2026.117559_bib0039","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.knosys.2018.11.031","article-title":"Mini-batch algorithms with online step size","volume":"165","author":"Yang","year":"2019","journal-title":"Knowl. Based Syst."},{"issue":"10","key":"10.1016\/j.cam.2026.117559_bib0040","doi-asserted-by":"crossref","first-page":"4627","DOI":"10.1109\/TNNLS.2020.3025383","article-title":"A minibatch proximal stochastic recursive gradient algorithm using a trust-region-like scheme and barzilai\u2013Borwein stepsizes","volume":"32","author":"Yu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.cam.2026.117559_bib0041","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1137\/120880811","article-title":"Stochastic first-and zeroth-order methods for nonconvex stochastic programming","volume":"23","author":"Ghadimi","year":"2013","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.cam.2026.117559_bib0042","series-title":"International Conference on Machine Learning","first-page":"78","article-title":"A lower bound for the optimization of finite sums","author":"Agarwal","year":"2015"},{"issue":"103","key":"10.1016\/j.cam.2026.117559_bib0043","first-page":"1","article-title":"Stochastic nested variance reduction for nonconvex optimization","volume":"21","author":"Zhou","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cam.2026.117559_bib0044","series-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","first-page":"795","article-title":"Linear convergence of gradient and proximal-gradient methods under the polyak-\u0142ojasiewicz condition","author":"Karimi","year":"2016"},{"key":"10.1016\/j.cam.2026.117559_bib0045","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1007\/s11590-016-1058-9","article-title":"The restricted strong convexity revisited: analysis of equivalence to error bound and quadratic growth","volume":"11","author":"Zhang","year":"2017","journal-title":"Optim. Lett."},{"key":"10.1016\/j.cam.2026.117559_bib0046","unstructured":"P. Gong, J. Ye, Linear convergence of variance-reduced stochastic gradient without strong convexity, (2014). arXiv preprint arXiv: 1406.1102."},{"key":"10.1016\/j.cam.2026.117559_bib0047","series-title":"First-order methods in optimization","author":"Beck","year":"2017"},{"key":"10.1016\/j.cam.2026.117559_bib0048","series-title":"Introductory lectures on convex optimization: A basic course","volume":"87","author":"Nesterov","year":"2003"},{"issue":"4","key":"10.1016\/j.cam.2026.117559_bib0049","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1137\/140961791","article-title":"A proximal stochastic gradient method with progressive variance reduction","volume":"24","author":"Xiao","year":"2014","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.cam.2026.117559_bib0050","unstructured":"Z. Wang, K. Ji, Y. Zhou, Y. Liang, V. Tarokh, Spiderboost: A class of faster variance-reduced algorithms for nonconvex optimization, arXiv 2018(2018)."},{"key":"10.1016\/j.cam.2026.117559_bib0051","unstructured":"C.-C. Chang, Libsvm data: Classification, regression, and multi-label, (2008). http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets\/."},{"key":"10.1016\/j.cam.2026.117559_bib0052","unstructured":"S.J. Reddi, S. Kale, S. Kumar, On the convergence of adam and beyond, (2019). arXiv preprint arXiv: 1904.09237."},{"key":"10.1016\/j.cam.2026.117559_bib0053","series-title":"International Conference on Machine Learning","first-page":"314","article-title":"Stochastic variance reduction for nonconvex optimization","author":"Reddi","year":"2016"}],"container-title":["Journal of Computational and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0377042726002128?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0377042726002128?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T12:13:49Z","timestamp":1786450429000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0377042726002128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":53,"alternative-id":["S0377042726002128"],"URL":"https:\/\/doi.org\/10.1016\/j.cam.2026.117559","relation":{},"ISSN":["0377-0427"],"issn-type":[{"value":"0377-0427","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An adaptive stochastic gradient method with variance reduction for smooth optimization problems","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational and Applied Mathematics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cam.2026.117559","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"117559"}}