{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T07:04:35Z","timestamp":1719990275194},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational and Applied Mathematics"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1016\/j.cam.2023.115425","type":"journal-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T20:48:32Z","timestamp":1687898912000},"page":"115425","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems"],"prefix":"10.1016","volume":"436","author":[{"given":"Zhen-Ping","family":"Yang","sequence":"first","affiliation":[]},{"given":"Yong","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.cam.2023.115425_b1","series-title":"OR Tools and Applications: Glimpses of Future Technologies","first-page":"38","article-title":"Coherent approaches to risk in optimization under uncertainty","author":"Rockafellar","year":"2007"},{"key":"10.1016\/j.cam.2023.115425_b2","series-title":"Theory Driven By Influential Applications","first-page":"168","article-title":"Advances in risk-averse optimization","author":"Ruszczy\u0144ski","year":"2013"},{"key":"10.1016\/j.cam.2023.115425_b3","series-title":"Proceedings of the 36th International Conference on Machine Learning, Vol. 97","first-page":"7454","article-title":"A composite randomized incremental gradient method","author":"Zhang","year":"2019"},{"issue":"6","key":"10.1016\/j.cam.2023.115425_b4","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1109\/TAC.2008.925853","article-title":"Stochastic approximation approaches to the stochastic variational inequality problem","volume":"53","author":"Jiang","year":"2008","journal-title":"IEEE Trans. Automat. Control"},{"issue":"3","key":"10.1016\/j.cam.2023.115425_b5","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TAC.2012.2215413","article-title":"Regularized iterative stochastic approximation methods for stochastic variational inequality problems","volume":"58","author":"Koshal","year":"2013","journal-title":"IEEE Trans. Automat. Control"},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b6","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/s10107-017-1175-y","article-title":"On smoothing, regularization, and averaging in stochastic approximation methods for stochastic variational inequality problems","volume":"165","author":"Yousefian","year":"2017","journal-title":"Math. Program."},{"issue":"2","key":"10.1016\/j.cam.2023.115425_b7","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/s10107-014-0769-x","article-title":"Incremental constraint projection methods for variational inequalities","volume":"150","author":"Wang","year":"2015","journal-title":"Math. Program."},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b8","first-page":"236","article-title":"Incremental constraint projection methods for monotone stochastic variational inequalities","volume":"44","author":"Iusem","year":"2018","journal-title":"Math. Oper. Res."},{"issue":"2","key":"10.1016\/j.cam.2023.115425_b9","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1137\/15M1031953","article-title":"Extragradient method with variance reduction for stochastic variational inequalities","volume":"27","author":"Iusem","year":"2017","journal-title":"SIAM J. Optim."},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b10","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1137\/17M1144799","article-title":"Variance-based extragradient methods with line search for stochastic variational inequalities","volume":"29","author":"Iusem","year":"2019","journal-title":"SIAM J. Optim."},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b11","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1137\/18M1230542","article-title":"A single time-scale stochastic approximation method for nested stochastic optimization","volume":"30","author":"Ghadimi","year":"2020","journal-title":"SIAM J. Optim."},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b12","first-page":"809","article-title":"Policy evaluation with temporal differences: A survey and comparison","volume":"15","author":"Dann","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cam.2023.115425_b13","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"1998"},{"issue":"1\u20132","key":"10.1016\/j.cam.2023.115425_b14","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s10107-016-1017-3","article-title":"Stochastic compositional gradient descent: Algorithms for minimizing compositions of expected-value functions","volume":"161","author":"Wang","year":"2017","journal-title":"Math. Program."},{"key":"10.1016\/j.cam.2023.115425_b15","first-page":"1","article-title":"Accelerating stochastic composition optimization","volume":"18","author":"Wang","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cam.2023.115425_b16","series-title":"Iterative Solution of Nonlinear Equations in Several Variables","author":"Ortega","year":"1970"},{"issue":"1\u20132","key":"10.1016\/j.cam.2023.115425_b17","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1007\/s10107-021-01709-z","article-title":"Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization","volume":"195","author":"Zhang","year":"2022","journal-title":"Math. Program."},{"issue":"46","key":"10.1016\/j.cam.2023.115425_b18","doi-asserted-by":"crossref","first-page":"22924","DOI":"10.1073\/pnas.1908018116","article-title":"The importance of better models in stochastic optimization","volume":"116","author":"Asi","year":"2019","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"3","key":"10.1016\/j.cam.2023.115425_b19","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.1137\/18M1230323","article-title":"Stochastic (approximate) proximal point methods: Convergence, optimality, and adaptivity","volume":"29","author":"Asi","year":"2019","journal-title":"SIAM J. Optim."},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b20","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1137\/18M1178244","article-title":"Stochastic model-based minimization of weakly convex functions","volume":"29","author":"Davis","year":"2019","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.cam.2023.115425_b21","unstructured":"Yu.M. Ermoliev, Methods of Stochastic Programming, Nauka, Moscow, 1976."},{"key":"10.1016\/j.cam.2023.115425_b22","unstructured":"X. Lian, M. Wang, J. Liu, Finite-sum composition optimization via variance reduced gradient descent, in: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS, 2017, pp. 1159\u20131167."},{"key":"10.1016\/j.cam.2023.115425_b23","unstructured":"W. Hu, C.J. Li, X. Lian, J. Liu, H. Yuan, Efficient smooth non-convex stochastic compositional optimization via stochastic recursive gradient descent, in: Proceedings of the 32nd Advances in Neural Information Processing Systems, 2019, pp. 6926\u20136935."},{"issue":"9","key":"10.1016\/j.cam.2023.115425_b24","first-page":"5813","article-title":"Variance reduced methods for non-convex composition optimization","volume":"44","author":"Liu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cam.2023.115425_b25","series-title":"Stochastic recursive momentum method for non-convex compositional optimization","author":"Yuan","year":"2020"},{"key":"10.1016\/j.cam.2023.115425_b26","series-title":"Compositional adam: An adaptive compositional solver","author":"Tutunov","year":"2022"},{"key":"10.1016\/j.cam.2023.115425_b27","series-title":"Unbiased simulation for optimizing stochastic function compositions","author":"Blanchet","year":"2017"},{"key":"10.1016\/j.cam.2023.115425_b28","unstructured":"Y. Hu, S. Zhang, X. Chen, N. He, Biased stochastic first-order methods for conditional stochastic optimization and applications in meta learning, in: Proceedings of the 33rd Advances in Neural Information Processing Systems, 2020, pp. 2759\u20132770."},{"key":"10.1016\/j.cam.2023.115425_b29","series-title":"Tighter analysis of alternating stochastic gradient method for stochastic nested problems","author":"Chen","year":"2021"},{"key":"10.1016\/j.cam.2023.115425_b30","series-title":"Proceedings of the 39th International Conference on Machine Learning, Vol. 162","first-page":"23292","article-title":"Finite-sum coupled compositional stochastic optimization: Theory and applications","author":"Wang","year":"2022"},{"key":"10.1016\/j.cam.2023.115425_b31","doi-asserted-by":"crossref","first-page":"4937","DOI":"10.1109\/TSP.2021.3092377","article-title":"Solving stochastic compositional optimization is nearly as easy as solving stochastic optimization","volume":"69","author":"Chen","year":"2021","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.cam.2023.115425_b32","unstructured":"H. Gao, H. Huang, Fast training method for stochastic compositional optimization problems, in: Proceedings of the 34th Advances in Neural Information Processing Systems, 2021, pp. 25334\u201325345."},{"key":"10.1016\/j.cam.2023.115425_b33","series-title":"Distributed stochastic compositional optimization problems over directed networks","author":"Zhao","year":"2022"},{"key":"10.1016\/j.cam.2023.115425_b34","doi-asserted-by":"crossref","unstructured":"Z. Huo, B. Gu, J. Liu, H. Huang, Accelerated method for stochastic composition optimization with nonsmooth regularization, in: Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018, pp. 3287\u20133294.","DOI":"10.1609\/aaai.v32i1.11795"},{"issue":"4","key":"10.1016\/j.cam.2023.115425_b35","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1109\/TNNLS.2018.2866699","article-title":"Duality-free methods for stochastic composition optimization","volume":"30","author":"Liu","year":"2018","journal-title":"IEEE Trans. Neural. Netw. Learn. Syst."},{"key":"10.1016\/j.cam.2023.115425_b36","doi-asserted-by":"crossref","unstructured":"P. Wang, R. Liu, N. Zheng, Z. Gong, Asynchronous proximal stochastic gradient algorithm for composition optimization problems, in: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019, pp. 1633\u20131640.","DOI":"10.1609\/aaai.v33i01.33011633"},{"key":"10.1016\/j.cam.2023.115425_b37","doi-asserted-by":"crossref","unstructured":"T. Lin, C. Fan, M. Wang, M.I. Jordan, Improved sample complexity for stochastic compositional variance reduced gradient, in: Proceedings of the 2020 American Control Conference, ACC, 2020, pp. 126\u2013131.","DOI":"10.23919\/ACC45564.2020.9147515"},{"issue":"4","key":"10.1016\/j.cam.2023.115425_b38","first-page":"418","article-title":"Katyusha acceleration for convex finite-sum compositional optimization","volume":"3","author":"Xu","year":"2021","journal-title":"INFORMS J. Comput."},{"issue":"1","key":"10.1016\/j.cam.2023.115425_b39","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1137\/18M1164846","article-title":"Multilevel stochastic gradient methods for nested composition optimization","volume":"29","author":"Yang","year":"2019","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.cam.2023.115425_b40","series-title":"Optimal algorithms for convex nested stochastic composite optimization","author":"Zhang","year":"2022"},{"issue":"3","key":"10.1016\/j.cam.2023.115425_b41","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1137\/20M1312952","article-title":"A stochastic subgradient method for nonsmooth nonconvex multilevel composition optimization","volume":"59","author":"Ruszczy\u0144ski","year":"2021","journal-title":"SIAM J. Control Optim."},{"issue":"2","key":"10.1016\/j.cam.2023.115425_b42","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1137\/19M1285457","article-title":"Multilevel composite stochastic optimization via nested variance reduction","volume":"31","author":"Zhang","year":"2021","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.cam.2023.115425_b43","series-title":"A projection-free algorithm for constrained stochastic multi-level composition optimization","author":"Xiao","year":"2022"},{"issue":"2","key":"10.1016\/j.cam.2023.115425_b44","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1137\/21M1406222","article-title":"Stochastic multilevel composition optimization algorithms with level-independent convergence rates","volume":"32","author":"Balasubramanian","year":"2022","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.cam.2023.115425_b45","series-title":"Proceedings of the 39th International Conference on Machine Learning, Vol. 162","first-page":"10195","article-title":"Optimal algorithms for stochastic multi-level compositional optimization","author":"Jiang","year":"2022"},{"key":"10.1016\/j.cam.2023.115425_b46","unstructured":"J. Zhang, L. Xiao, A stochastic composite gradient method with incremental variance reduction, in: Proceedings of the 32nd Advances in Neural Information Processing Systems, 2019, pp. 9078\u20139088."},{"key":"10.1016\/j.cam.2023.115425_b47","series-title":"Nearly optimal robust method for convex compositional problems with heavy-tailed noise","author":"Yan","year":"2020"},{"key":"10.1016\/j.cam.2023.115425_b48","series-title":"Momentum with variance reduction for nonconvex composition optimization","author":"Chen","year":"2020"},{"key":"10.1016\/j.cam.2023.115425_b49","series-title":"Proceedings of the 37th International Conference on Machine Learning, Vol. 119","first-page":"9572","article-title":"Stochastic Gauss\u2013Newton algorithms for nonconvex compositional optimization","author":"Tran-Dinh","year":"2020"},{"key":"10.1016\/j.cam.2023.115425_b50","doi-asserted-by":"crossref","first-page":"4621","DOI":"10.1007\/s12190-022-01722-1","article-title":"Stochastic Gauss\u2013Newton algorithm with STORM estimators for nonconvex composite optimization","volume":"68","author":"Wang","year":"2022","journal-title":"J. Appl. Math. Comput."},{"key":"10.1016\/j.cam.2023.115425_b51","unstructured":"Q. Tran-Dinh, D. Liu, L. Nguyen, Hybrid variance-reduced SGD algorithms for minimax problems with nonconvex-linear function, in: Proceedings of the 33rd Advances in Neural Information Processing Systems, 2020, pp. 11096\u201311107."},{"issue":"2","key":"10.1016\/j.cam.2023.115425_b52","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.cam.2023.115425_b53","series-title":"Proceedings of the 34th International Conference on Machine Learning, Vol. 70","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.2023.115425_b54","unstructured":"A. Cutkosky, F. Orabona, Momentum-based variance reduction in non-convex SGD, in: Proceedings of the 32nd Advances in Neural Information Processing Systems, 2019, pp. 15210\u201315219."}],"container-title":["Journal of Computational and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0377042723003692?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0377042723003692?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T15:44:06Z","timestamp":1697125446000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0377042723003692"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":54,"alternative-id":["S0377042723003692"],"URL":"https:\/\/doi.org\/10.1016\/j.cam.2023.115425","relation":{},"ISSN":["0377-0427"],"issn-type":[{"value":"0377-0427","type":"print"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection 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.2023.115425","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"115425"}}