{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T17:01:42Z","timestamp":1766077302458,"version":"3.48.0"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012334","name":"Graduate Scientific Research and Innovation Foundation of Chongqing","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012334","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11971078"],"award-info":[{"award-number":["11971078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.engappai.2025.113087","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T23:46:33Z","timestamp":1762818393000},"page":"113087","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P3","title":["Inertial proximal stochastic gradient method with adaptive sampling for non-convex and non-smooth problems"],"prefix":"10.1016","volume":"163","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1139-9478","authenticated-orcid":false,"given":"Mengxiang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Shengjie","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2025.113087_b1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.58496\/BJN\/2023\/004","article-title":"A survey on the significance of artificial intelligence (ai) in network cybersecurity","volume":"2023","author":"Ali","year":"2023","journal-title":"Babylon. J. Netw."},{"key":"10.1016\/j.engappai.2025.113087_b2","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM J. Imaging Sci."},{"key":"10.1016\/j.engappai.2025.113087_b3","doi-asserted-by":"crossref","first-page":"3729","DOI":"10.1093\/imanum\/drac083","article-title":"Adaptive sampling strategies for risk-averse stochastic optimization with constraints","volume":"43","author":"Beiser","year":"2023","journal-title":"IMA J. Numer. Anal."},{"key":"10.1016\/j.engappai.2025.113087_b4","doi-asserted-by":"crossref","first-page":"3312","DOI":"10.1137\/17M1154679","article-title":"Adaptive sampling strategies for stochastic optimization","volume":"28","author":"Bollapragada","year":"2018","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.engappai.2025.113087_b5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s13675-015-0045-8","article-title":"An inertial forward\u2013backward algorithm for the minimization of the sum of two nonconvex functions","volume":"4","author":"Bo\u0163","year":"2016","journal-title":"EURO J. Comput. Optim."},{"key":"10.1016\/j.engappai.2025.113087_b6","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1137\/16M1080173","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"Bottou","year":"2018","journal-title":"SIAM Rev."},{"key":"10.1016\/j.engappai.2025.113087_b7","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s10107-012-0572-5","article-title":"Sample size selection in optimization methods for machine learning","volume":"134","author":"Byrd","year":"2012","journal-title":"Math. Program."},{"key":"10.1016\/j.engappai.2025.113087_b8","article-title":"Momentum-based variance reduction in non-convex sgd","volume":"vol. 32","author":"Cutkosky","year":"2019"},{"key":"10.1016\/j.engappai.2025.113087_b9","article-title":"Saga: A fast incremental gradient method with support for non-strongly convex composite objectives","volume":"vol. 27","author":"Defazio","year":"2014"},{"key":"10.1016\/j.engappai.2025.113087_b10","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.engappai.2025.113087_b11","series-title":"2015 European Control Conference","first-page":"310","article-title":"Global convergence of the heavy-ball method for convex optimization","author":"Ghadimi","year":"2015"},{"key":"10.1016\/j.engappai.2025.113087_b12","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s10107-015-0871-8","article-title":"Accelerated gradient methods for nonconvex nonlinear and stochastic programming","volume":"156","author":"Ghadimi","year":"2016","journal-title":"Math. Program."},{"key":"10.1016\/j.engappai.2025.113087_b13","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s10107-014-0846-1","article-title":"Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization","volume":"155","author":"Ghadimi","year":"2016","journal-title":"Math. Program."},{"year":"2017","series-title":"Accurate, large minibatch SGD: Training imagenet in 1 h","author":"Goyal","key":"10.1016\/j.engappai.2025.113087_b14"},{"key":"10.1016\/j.engappai.2025.113087_b15","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10957-025-02771-9","article-title":"Non-asymptotic analysis of hybrid spg for non-convex stochastic composite optimization","volume":"207","author":"He","year":"2025","journal-title":"J. Optim. Theory Appl."},{"key":"10.1016\/j.engappai.2025.113087_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119546","article-title":"Nonconvex optimization with inertial proximal stochastic variance reduction gradient","volume":"648","author":"He","year":"2023","journal-title":"Inform. Sci."},{"key":"10.1016\/j.engappai.2025.113087_b17","article-title":"Generalize better: closing the generalization gap in large batch training of neural networks","volume":"vol. 30","author":"Hoffer","year":"2017"},{"key":"10.1016\/j.engappai.2025.113087_b18","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1287\/stsy.2022.0095","article-title":"Smoothed variable sample-size accelerated proximal methods for nonsmooth stochastic convex programs","volume":"12","author":"Jalilzadeh","year":"2022","journal-title":"Stoch. Syst."},{"key":"10.1016\/j.engappai.2025.113087_b19","series-title":"International Conference on Machine Learning","first-page":"1724","article-title":"How to escape saddle points efficiently","author":"Jin","year":"2017"},{"key":"10.1016\/j.engappai.2025.113087_b20","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume":"vol. 26","author":"Johnson","year":"2013"},{"year":"2014","series-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","key":"10.1016\/j.engappai.2025.113087_b21"},{"key":"10.1016\/j.engappai.2025.113087_b22","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1137\/23M1582345","article-title":"Iml fista: A multilevel framework for inexact and inertial forward\u2013backward. application to image restoration","volume":"17","author":"Lauga","year":"2024","journal-title":"SIAM J. Imaging Sci."},{"key":"10.1016\/j.engappai.2025.113087_b23","article-title":"Accelerated proximal gradient methods for nonconvex programming","volume":"vol. 28","author":"Li","year":"2015"},{"key":"10.1016\/j.engappai.2025.113087_b24","first-page":"1","article-title":"Stochastic modified equations and dynamics of stochastic gradient algorithms i: Mathematical foundations","volume":"20","author":"Li","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2025.113087_b25","series-title":"Proceedings of the 34th International Conference on Machine Learning","first-page":"2111","article-title":"Convergence analysis of proximal gradient with momentum for nonconvex optimization","volume":"vol. 70","author":"Li","year":"2017"},{"year":"2018","series-title":"An empirical model of large-batch training","author":"McCandlish","key":"10.1016\/j.engappai.2025.113087_b26"},{"key":"10.1016\/j.engappai.2025.113087_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.70470\/EDRAAK\/2025\/001","article-title":"Explainable ai for healthcare: Training healthcare workers to use artificial intelligence techniques to reduce medical negligence in ghana\u2019s public health act, 2012 (act 851)","volume":"2025","author":"Mensah","year":"2025","journal-title":"Edraak"},{"year":"2014","series-title":"Freund\u2019s Mathematical Statistics with Applications","author":"Miller","key":"10.1016\/j.engappai.2025.113087_b28"},{"key":"10.1016\/j.engappai.2025.113087_b29","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1137\/070704277","article-title":"Robust stochastic approximation approach to stochastic programming","volume":"19","author":"Nemirovski","year":"2009","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.engappai.2025.113087_b30","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate O(1\/k2)","volume":"vol. 269","author":"Nesterov","year":"1983"},{"volume":"vol. 87","year":"2003","author":"Nesterov","key":"10.1016\/j.engappai.2025.113087_b31"},{"key":"10.1016\/j.engappai.2025.113087_b32","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.engappai.2025.113087_b33","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1109\/TETCI.2021.3058672","article-title":"Learning sparse neural networks using non-convex regularization","volume":"6","author":"Pandit","year":"2021","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.engappai.2025.113087_b34","first-page":"4455","article-title":"Proxsarah: An efficient algorithmic framework for stochastic composite nonconvex optimization","volume":"21","author":"Pham","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2025.113087_b35","article-title":"Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization","volume":"vol. 29","author":"Reddi","year":"2016"},{"key":"10.1016\/j.engappai.2025.113087_b36","series-title":"Optimizing Methods in Statistics","first-page":"233","article-title":"A convergence theorem for non negative almost supermartingales and some applications","author":"Robbins","year":"1971"},{"volume":"vol. 317","year":"2009","author":"Rockafellar","key":"10.1016\/j.engappai.2025.113087_b37"},{"key":"10.1016\/j.engappai.2025.113087_b38","article-title":"A stochastic gradient method with an exponential convergence _rate for finite training sets","volume":"vol. 25","author":"Roux","year":"2012"},{"key":"10.1016\/j.engappai.2025.113087_b39","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s10107-016-1030-6","article-title":"Minimizing finite sums with the stochastic average gradient","volume":"162","author":"Schmidt","year":"2017","journal-title":"Math. Program."},{"key":"10.1016\/j.engappai.2025.113087_b40","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2316301121","article-title":"On the different regimes of stochastic gradient descent","volume":"121","author":"Sclocchi","year":"2024","journal-title":"Proc. Natl. Acad. Sci."},{"year":"2017","series-title":"Don\u2019t decay the learning rate, increase the batch size","author":"Smith","key":"10.1016\/j.engappai.2025.113087_b41"},{"key":"10.1016\/j.engappai.2025.113087_b42","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1007\/s10107-020-01583-1","article-title":"A hybrid stochastic optimization framework for composite nonconvex optimization","volume":"191","author":"Tran-Dinh","year":"2022","journal-title":"Math. Program."},{"key":"10.1016\/j.engappai.2025.113087_b43","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."},{"year":"2020","series-title":"Constrained and composite optimization via adaptive sampling methods","author":"Xie","key":"10.1016\/j.engappai.2025.113087_b44"},{"key":"10.1016\/j.engappai.2025.113087_b45","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1093\/imanum\/drad020","article-title":"Constrained and composite optimization via adaptive sampling methods","volume":"44","author":"Xie","year":"2024","journal-title":"IMA J. Numer. Anal."},{"key":"10.1016\/j.engappai.2025.113087_b46","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1109\/TNNLS.2012.2197412","article-title":"l1\/2 Regularization: A thresholding representation theory and a fast solver","volume":"23","author":"Xu","year":"2012","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.engappai.2025.113087_b47","article-title":"Non-asymptotic analysis of stochastic methods for non-smooth non-convex regularized problems","volume":"vol. 32","author":"Xu","year":"2019"},{"key":"10.1016\/j.engappai.2025.113087_b48","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1007\/s10957-022-02132-w","article-title":"Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization","volume":"196","author":"Xu","year":"2023","journal-title":"J. Optim. Theory Appl."},{"key":"10.1016\/j.engappai.2025.113087_b49","doi-asserted-by":"crossref","unstructured":"Yao, Q., Kwok, J.T.Y., Gao, F., Chen, W., y. Liu, T., 2017. Efficient inexact proximal gradient algorithm for nonconvex problems. In: IJCAI International Joint Conference on Artificial Intelligence.","DOI":"10.24963\/ijcai.2017\/462"},{"key":"10.1016\/j.engappai.2025.113087_b50","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10915-024-02748-2","article-title":"A proximal stochastic quasi-Newton algorithm with dynamical sampling and stochastic line search","volume":"102","author":"Zhang","year":"2025","journal-title":"J. Sci. Comput."},{"key":"10.1016\/j.engappai.2025.113087_b51","article-title":"Which algorithmic choices matter at which batch sizes? insights from a noisy quadratic model","volume":"vol. 32","author":"Zhang","year":"2019"},{"key":"10.1016\/j.engappai.2025.113087_b52","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1109\/TCYB.2022.3157892","article-title":"Double sparse deep reinforcement learning via multilayer sparse coding and nonconvex regularized pruning","volume":"53","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Cybern."},{"year":"2023","series-title":"Revisiting lq (0\u2264q<1) norm regularized optimization","author":"Zhou","key":"10.1016\/j.engappai.2025.113087_b53"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625031185?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197625031185?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T16:56:39Z","timestamp":1766076999000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197625031185"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":53,"alternative-id":["S0952197625031185"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2025.113087","relation":{},"ISSN":["0952-1976"],"issn-type":[{"type":"print","value":"0952-1976"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Inertial proximal stochastic gradient method with adaptive sampling for non-convex and non-smooth problems","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2025.113087","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113087"}}