{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T18:41:00Z","timestamp":1775155260044,"version":"3.50.1"},"reference-count":60,"publisher":"Informa UK Limited","issue":"5","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11331012"],"award-info":[{"award-number":["11331012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11301505"],"award-info":[{"award-number":["11301505"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11731013"],"award-info":[{"award-number":["11731013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11688101"],"award-info":[{"award-number":["11688101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Optimization Methods and Software"],"published-print":{"date-parts":[[2019,9,3]]},"DOI":"10.1080\/10556788.2018.1471141","type":"journal-article","created":{"date-parts":[[2018,5,18]],"date-time":"2018-05-18T11:46:36Z","timestamp":1526643996000},"page":"922-948","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":21,"title":["Stochastic proximal quasi-Newton methods for non-convex composite optimization"],"prefix":"10.1080","volume":"34","author":[{"given":"Xiaoyu","family":"Wang","sequence":"first","affiliation":[{"name":"LSEC, Institute of Computational Mathematics and Scientific\/Engineering Computing, AMSS, Chinese Academy of Sciences, Beijing, People's Republic of China"},{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya-xiang","family":"Yuan","sequence":"additional","affiliation":[{"name":"LSEC, Institute of Computational Mathematics and Scientific\/Engineering Computing, AMSS, Chinese Academy of Sciences, Beijing, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2018,5,18]]},"reference":[{"issue":"116","key":"CIT0001","first-page":"1","volume":"18","author":"Agarwal N.","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"CIT0002","unstructured":"Z. Allen-Zhu,Natasha 2: Faster non-convex optimization than SGD, preprint (2017). Available at arXiv:1708.08694v2."},{"key":"CIT0003","unstructured":"Z. Allen-Zhu,Natasha: Faster stochastic non-convex optimization via strongly non-convex parameter, preprint (2017). Available at arXiv:1702.00763."},{"key":"CIT0004","unstructured":"Z. Allen-Zhu and E. Hazan,Variance reduction for faster non-convex optimization, International Conference on Machine Learning, New York, NY, 2016, pp. 699\u2013707."},{"key":"CIT0005","unstructured":"S. Becker and J. Fadili,A quasi-Newton proximal splitting method, Advances in Neural Information Processing Systems, Lake Tahoe, 2012, pp. 2618\u20132626."},{"key":"CIT0006","unstructured":"A.S. Berahas, R. Bollapragada, and J. Nocedal,An investigation of Newton-sketch and subsampled Newton methods, preprint (2017). Available at arXiv:1705.06211."},{"key":"CIT0007","first-page":"1737","volume":"10","author":"Bordes A.","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"CIT0008","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0965-3"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1137\/140954362"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623493252985"},{"key":"CIT0011","unstructured":"R.H. Byrd, J. Nocedal, and F. Oztoprak,An inexact successive quadratic approximation method for convex l1 regularized optimization, preprint (2013). Available at arXiv:1309.3529."},{"key":"CIT0012","first-page":"536","volume":"25","author":"Cauchy A.L.","year":"1847","journal-title":"Comptes rendus des s\u00e9ances de l'Acad\u00e9mie des sciences de Paris"},{"key":"CIT0013","unstructured":"K. Cho, B. Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio,Learning phrase representations using rnn encoderdecoder for statistical machine translation, preprint (2014). Available at arXiv:1406.1078."},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.1007\/BF01594934"},{"key":"CIT0015","unstructured":"F.E. Curtis,A self-correcting variable-metric algorithm for stochastic optimization, International Conference on Machine Learning, New York, NY, 2016, pp. 632\u2013641."},{"key":"CIT0016","unstructured":"A. Defazio, F. Bach, and S.L. Julien,Saga: A fast incremental gradient method with support for non-strongly convex composite objectives, Advances in Neural Information Processing Systems, Montreal, 2014, pp. 1646\u20131654."},{"key":"CIT0017","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOAS131"},{"key":"CIT0018","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0846-1"},{"key":"CIT0019","unstructured":"H. Ghanbari and K. Scheinberg,Proximal quasi-Newton methods for regularized convex optimization with linear and accelerated sublinear convergence rates, preprint (2016). Available at arXiv:1607.03081."},{"key":"CIT0020","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016"},{"key":"CIT0021","unstructured":"C.J. Hsieh, M.A. Sustik, I.S. Dhillon, and P. Ravikumar,Sparse inverse covariance matrix estimation using quadratic approximation, Advances in Neural Information Processing Systems, Granada, 2011, pp. 2330\u20132338."},{"key":"CIT0022","unstructured":"R. Johnson and T. Zhang,Accelerating stochastic gradient descent using predictive variance reduction, Advances in Neural Information Processing Systems, Lake Tahoe, 2013, pp. 315\u2013323."},{"key":"CIT0023","doi-asserted-by":"crossref","unstructured":"H. Karimi, J. Nutini, and M. Schmidt,Linear convergence of gradient and proximal-gradient methods under the Polyak-\u0142ojasiewicz condition, Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, Riva del Garda, 2016, pp. 795\u2013811.","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"CIT0024","doi-asserted-by":"publisher","DOI":"10.1137\/140966587"},{"key":"CIT0025","doi-asserted-by":"publisher","DOI":"10.1137\/0803001"},{"key":"CIT0026","unstructured":"F.R. Khorasani and M.W. Mahoney,Sub-sampled Newton methods I: Globally convergent algorithms, preprint (2016). Available at arXiv:1601.04737."},{"key":"CIT0027","unstructured":"F.R. Khorasani and M.W. Mahoney,Sub-sampled Newton methods II: Local convergence rates, preprint (2016). Available at arXiv:1601.04738."},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1137\/08073812X"},{"key":"CIT0029","doi-asserted-by":"publisher","DOI":"10.1137\/130921428"},{"key":"CIT0030","unstructured":"H. Lin, J. Mairal, and Z. Harchaoui,A generic quasi-Newton algorithm for faster gradient-based optimization, preprint (2016). Available at arXiv:1610.00960."},{"key":"CIT0031","unstructured":"X. Liu, C. Hsieh, J.D. Lee, and Y. Sun,An inexact subsampled proximal Newton-type method for large-scale machine learning, preprint (2017). Available at arXiv:1708.08552."},{"key":"CIT0032","unstructured":"L. Luo, Z. Chen, Z. Zhang, and W. Li,A proximal stochastic quasi-Newton algorithm, preprint (2016). Available at arXiv:1602.00223."},{"key":"CIT0033","doi-asserted-by":"publisher","DOI":"10.1137\/140957639"},{"key":"CIT0034","doi-asserted-by":"publisher","DOI":"10.1007\/BF00935173"},{"key":"CIT0035","unstructured":"A. Mokhtari, M. Eisen, and A. Ribeiro,IQN: An incremental quasi-Newton method with local superlinear convergence rate, preprint (2017). Available at arXiv:1702.00709."},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2357775"},{"key":"CIT0037","unstructured":"P. Moritz, R. Nishihara, and M.I. Jordan,A linearly-convergent stochastic L-BFGS algorithm, Artificial Intelligence and Statistics, 2016, pp. 249\u2013258."},{"key":"CIT0038","volume-title":"Numerical Optimization","author":"Nocedal J.","year":"2006","edition":"2"},{"key":"CIT0039","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/19.4.497"},{"key":"CIT0040","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588967"},{"key":"CIT0041","doi-asserted-by":"crossref","unstructured":"S.J. Reddi, A. Hefny, S. Sra, B. P\u00f3czos, and A.J. Smola,Stochastic variance reduction for nonconvex optimization, International Conference on Machine Learning, New York, NY, 2016, pp. 314\u2013323.","DOI":"10.1109\/ALLERTON.2016.7852377"},{"key":"CIT0042","unstructured":"S.J. Reddi, S. Sra, B. P\u00f3czos, and A. Smola,Fast incremental method for nonconvex optimization, preprint (2016). Available at arXiv:1603.06159."},{"key":"CIT0043","unstructured":"S.J. Reddi, S. Sra, B. P\u00f3czos, and A. Smola,Fast stochastic methods for nonsmooth nonconvex optimization, preprint (2016). Available at arXiv:1605.06900."},{"key":"CIT0044","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"CIT0045","unstructured":"A. Rodomanov and D. Kropotov,A superlinearly-convergent proximal Newton-type method for the optimization of finite sums, International Conference on Machine Learning, New York, NY, 2016, pp. 2597\u20132605."},{"key":"CIT0046","first-page":"456","volume":"5","author":"Schmidt M.","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"CIT0047","doi-asserted-by":"crossref","unstructured":"M. Schmidt, D. Kim, and S. Sra,Projected Newton-type methods in machine learning, inOptimization for Machine Learning, S. Sra, S. Nowozin, and S.Wright, eds., MIT Press, Cambridge, MA, 2011.","DOI":"10.7551\/mitpress\/8996.003.0013"},{"key":"CIT0048","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"CIT0049","unstructured":"N.N. Schraudolph, J. Yu, and S. G\u00fcnte,A stochastic quasi-Newton method for online convex optimization, J. Mach. Learn. Res. 2 (2007), pp. 436\u2013443."},{"key":"CIT0050","unstructured":"S. Shalev-Shwartz and T. Zhang,Proximal stochastic dual coordinate ascent, preprint (2012). Available at arXiv:1211.2717."},{"issue":"1","key":"CIT0051","first-page":"567","volume":"14","author":"Shalev-Shwartz S.","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"CIT0052","doi-asserted-by":"crossref","unstructured":"Z. Shi and R. Liu,Large scale optimization with proximal stochastic Newton-type gradient descent, Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, 2015, pp. 691\u2013704.","DOI":"10.1007\/978-3-319-23528-8_43"},{"key":"CIT0053","first-page":"1865","volume":"12","author":"Shwartz S.","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"CIT0054","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011259905470"},{"issue":"1","key":"CIT0055","first-page":"23","volume":"27","author":"Sun L.P.","journal-title":"Comput. Optim. Appl."},{"key":"CIT0056","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"CIT0057","doi-asserted-by":"publisher","DOI":"10.1137\/15M1053141"},{"key":"CIT0058","doi-asserted-by":"publisher","DOI":"10.1137\/140961791"},{"key":"CIT0059","unstructured":"X. Yu and D. Tao,Variance-reduced proximal stochastic gradient descent for non-convex composite optimization, preprint (2016). Available at arXiv:1606.00602."},{"key":"CIT0060","first-page":"3183","volume":"11","author":"Yuan G.X.","year":"2010","journal-title":"J. Mach. Learn. Res."}],"container-title":["Optimization Methods and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/10556788.2018.1471141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T18:24:10Z","timestamp":1693679050000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/10556788.2018.1471141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,18]]},"references-count":60,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,9,3]]}},"alternative-id":["10.1080\/10556788.2018.1471141"],"URL":"https:\/\/doi.org\/10.1080\/10556788.2018.1471141","relation":{},"ISSN":["1055-6788","1029-4937"],"issn-type":[{"value":"1055-6788","type":"print"},{"value":"1029-4937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,18]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=goms20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=goms20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2018-01-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-04-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-05-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}