{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T11:50:31Z","timestamp":1759837831763,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Italian MIUR, Progetti di Ricerca di Rilevante Interesse Nazionale, GAUChO Project","award":["2015YPXH4W_004"],"award-info":[{"award-number":["2015YPXH4W_004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tnnls.2017.2785361","type":"journal-article","created":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T19:08:17Z","timestamp":1516043297000},"page":"4947-4956","source":"Crossref","is-referenced-by-count":8,"title":["Stochastic Training of Neural Networks via Successive Convex Approximations"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0881-8344","authenticated-orcid":false,"given":"Simone","family":"Scardapane","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4130-3177","authenticated-orcid":false,"given":"Paolo","family":"Di Lorenzo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1038\/ncomms5308","article-title":"Searching for exotic particles in high-energy physics with deep learning","volume":"5","author":"baldi","year":"2014","journal-title":"Nature Commun"},{"journal-title":"ADADELTA An Adaptive Learning Rate Method","year":"2012","author":"zeiler","key":"ref38"},{"key":"ref33","first-page":"348","article-title":"Manifold regularized deep neural networks","author":"tomar","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2188013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.029"},{"key":"ref30","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref36","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref35","first-page":"2113","article-title":"Gradient-based hyperparameter optimization through reversible learning","author":"maclaurin","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2399858"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2293126"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2531627"},{"key":"ref13","first-page":"4701","article-title":"Large-scale nonconvex stochastic optimization by doubly stochastic successive convex approximation","author":"mokhtari","year":"2017","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0701-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/120891009"},{"journal-title":"Parallel and distributed methods for nonconvex optimization—Part I Theory","year":"2014","author":"scutari","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2016.2524588"},{"journal-title":"Asynchronous parallel algorithms for nonconvex big-data optimization Model and convergence","year":"2016","author":"cannelli","key":"ref18"},{"key":"ref19","first-page":"1","article-title":"Parallel and distributed training of neural networks via successive convex approximation","author":"di lorenzo","year":"2016","journal-title":"Proc IEEE 26th Int Workshop Mach Learn Signal Process (MLSP)"},{"journal-title":"DeepAR Probabilistic forecasting with autoregressive recurrent networks","year":"2017","author":"flunkert","key":"ref28"},{"journal-title":"Learning activation functions to improve deep neural networks","year":"2014","author":"agostinelli","key":"ref4"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2006","author":"bishop","key":"ref27"},{"journal-title":"Optimization Methods for Large-Scale Machine Learning","year":"2016","author":"bottou","key":"ref3"},{"key":"ref6","first-page":"623","article-title":"A fast natural Newton method","author":"roux","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref5","article-title":"Observer-based adaptive fault-tolerant tracking control of nonlinear nonstrict-feedback systems","author":"wu","year":"0","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref8","first-page":"604","article-title":"Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods","author":"sohl-dickstein","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref7","first-page":"735","article-title":"Deep learning via hessian-free optimization","author":"martens","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref2","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.04.004"},{"key":"ref22","first-page":"3076","article-title":"A convergent and fully distributable SVMs training algorithm","author":"manno","year":"2016","journal-title":"Proc Int Joint Conf Neural Netw (IJCNN)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2016.04.007"},{"journal-title":"Mollifying networks","year":"2016","author":"gulcehre","key":"ref24"},{"key":"ref23","first-page":"123","article-title":"Convex neural networks","author":"bengio","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"The marginal value of adaptive gradient methods in machine learning","year":"2017","author":"wilson","key":"ref26"},{"key":"ref25","first-page":"iii-1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8468244\/08259365.pdf?arnumber=8259365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:28:57Z","timestamp":1642004937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8259365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":39,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2785361","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}