{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:55:54Z","timestamp":1773377754846,"version":"3.50.1"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/isit.2019.8849667","type":"proceedings-article","created":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T21:46:12Z","timestamp":1569534372000},"page":"2469-2473","source":"Crossref","is-referenced-by-count":4,"title":["Fitting ReLUs via SGD and Quantized SGD"],"prefix":"10.1109","author":[{"given":"Seyed Mohammadreza","family":"Mousavi Kalan","sequence":"first","affiliation":[{"name":"Ming Hsieh Department of Electrical Engineering, University of Southern, California, CA, USA"}]},{"given":"Mahdi","family":"Soltanolkotabi","sequence":"additional","affiliation":[{"name":"Ming Hsieh Department of Electrical Engineering, University of Southern, California, CA, USA"}]},{"given":"A. Salman","family":"Avestimehr","sequence":"additional","affiliation":[{"name":"Ming Hsieh Department of Electrical Engineering, University of Southern, California, CA, USA"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2674","article-title":"Taming the wild: A unified analysis of hogwild-style algorithms","author":"de sa","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref11","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2014-274","article-title":"1-bit stochastic gradient descent and application to data-parallel distributed training of speech dnns","author":"seide","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref13","article-title":"signsgd: compressed optimisation for non-convex problems","author":"bernstein","year":"0","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971309"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849667"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.advwatres.2011.04.013"},{"key":"ref4","article-title":"Learning relu networks via alternating minimization","author":"jagatap","year":"2018"},{"key":"ref3","article-title":"Learning relu networks on linearly separable data: Algorithm, optimality, and generalization","author":"wang","year":"2018"},{"key":"ref6","article-title":"Local geometry of one-hidden-layer neural networks for logistic regression","author":"fu","year":"2018"},{"key":"ref5","article-title":"Learning one-hidden-layer relu networks via gradient descent","author":"zhang","year":"2018"},{"key":"ref8","article-title":"Convergence analysis of two-layer neural networks with relu activation","author":"li","year":"2017","journal-title":"NIPS"},{"key":"ref7","article-title":"Minimizing nonconvex population risk from rough empirical risk","author":"jin","year":"2018","journal-title":"CoRR"},{"key":"ref2","article-title":"Learning relus via gradient descent","volume":"30","author":"soltanolkotabi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"1709","author":"alistarh","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref9","first-page":"5129","article-title":"Gradiveq: Vector quantization for bandwidth-efficient gradient aggregation in distributed cnn training","author":"yu","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 IEEE International Symposium on Information Theory (ISIT)","location":"Paris, France","start":{"date-parts":[[2019,7,7]]},"end":{"date-parts":[[2019,7,12]]}},"container-title":["2019 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8827389\/8849208\/08849667.pdf?arnumber=8849667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:04Z","timestamp":1773347704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8849667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/isit.2019.8849667","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}