{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T07:48:05Z","timestamp":1768895285293,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/bigdata47090.2019.9005621","type":"proceedings-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T06:05:34Z","timestamp":1582610734000},"page":"94-104","source":"Crossref","is-referenced-by-count":3,"title":["On the Global Convergence of Continuous\u2013Time Stochastic Heavy\u2013Ball Method for Nonconvex Optimization"],"prefix":"10.1109","author":[{"given":"Wenqing","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris Junchi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.62"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/401"},{"key":"ref31","article-title":"DBSDA: Lowering the Bound of Misclassification Rate for Sparse Linear Discriminant Analysis via Model Debiasing","author":"xiong","year":"2018","journal-title":"IEEE Transactions onNeural Networks and Learning Systems"},{"key":"ref30","author":"yosida","year":"1965","journal-title":"Functional Analysis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/415\/07865"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-25847-3","author":"freidlin","year":"2012","journal-title":"Random Perturbations of Dynamical Systems"},{"key":"ref12","first-page":"797","article-title":"Escaping from saddle points – online stochastic gradient for tensor decomposition","author":"ge","year":"2015","journal-title":"Proc 28th Conf Learn Theory"},{"key":"ref13","article-title":"On the fast convergence of random perturbations of the gradient flow","author":"hu","year":"2017","journal-title":"arXiv 1706 00837"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4310\/AMSA.2019.v4.n1.a1"},{"key":"ref15","first-page":"1724","article-title":"How to escape saddle points efficiently","author":"jin","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"Accelerated gradient descent escapes saddle points faster than gradient descent","author":"jin","year":"2017","journal-title":"arXiv preprint arXiv 1711 11585"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809187"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF02761819"},{"key":"ref19","volume":"35","author":"kushner","year":"2003","journal-title":"Stochastic Approximation and Recursive Algorithms and Applications"},{"key":"ref28","article-title":"When are nonconvex problems not scary?","author":"sun","year":"2015","journal-title":"arXiv preprint arXiv 1510 06096"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","author":"borkar","year":"2008","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref27","first-page":"1","article-title":"A differential equation for modeling Nesterov’s accelerated gradient method: theory and insights","volume":"17","author":"su","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","author":"benveniste","year":"2012","journal-title":"Adaptive Algorithms and Stochastic Approximations"},{"key":"ref6","first-page":"1163","article-title":"Escaping saddles with stochastic gradients","author":"daneshmand","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref29","article-title":"On the importance of initialization and momentum in deep learning","volume":"28","author":"sutskever","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0143385700000043"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1022855739"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(95)00063-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-010-0264-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4149(01)00083-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1037-5"},{"key":"ref20","first-page":"1246","article-title":"Gradient descent only converges to minimizers","author":"lee","year":"2016","journal-title":"Proceedings of the 29th Conference on Learning Theory"},{"key":"ref22","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":"Journal of Machine Learning Research"},{"key":"ref21","first-page":"2101","article-title":"Stochastic modified equations and adaptive stochastic gradient algorithms","author":"li","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref24","author":"milnor","year":"1963","journal-title":"Morse Lemma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2969\/jmsj\/05010095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref25","article-title":"Behavior of accelerated gradient methods near critical points of non–convex problems","author":"o\u2019neill","year":"2017","journal-title":"arXiv 1706 07993v1[MATH OC]"}],"event":{"name":"2019 IEEE International Conference on Big Data (Big Data)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2019,12,9]]},"end":{"date-parts":[[2019,12,12]]}},"container-title":["2019 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8986695\/9005444\/09005621.pdf?arnumber=9005621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:56:02Z","timestamp":1658094962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9005621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/bigdata47090.2019.9005621","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}