{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:19:26Z","timestamp":1774628366902,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9378178","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T21:10:21Z","timestamp":1616188221000},"page":"718-727","source":"Crossref","is-referenced-by-count":2,"title":["Communication-Efficient Local Stochastic Gradient Descent for Scalable Deep Learning"],"prefix":"10.1109","author":[{"given":"Sunwoo","family":"Lee","sequence":"first","affiliation":[]},{"given":"Qiao","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Ankit","family":"Agrawal","sequence":"additional","affiliation":[]},{"given":"Alok","family":"Choudhary","sequence":"additional","affiliation":[]},{"given":"Wei-keng","family":"Liao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2018.8638635"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SHPCC.1994.296665"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(06)80021-9"},{"key":"ref14","article-title":"A new optimized mpi reduce and allreduce algorithm","author":"rabenseifner","year":"1997"},{"key":"ref15","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016"},{"key":"ref16","article-title":"Adding gradient noise improves learning for very deep networks","author":"neelakantan","year":"2015"},{"key":"ref17","article-title":"Towards understanding the importance of noise in training neural networks","author":"zhou","year":"2019"},{"key":"ref18","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"goyal","year":"2017"},{"key":"ref19","first-page":"1731","article-title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","author":"hoffer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2017.00030"},{"key":"ref5","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update sgd","author":"wang","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015289"},{"key":"ref7","article-title":"Tictac: Accelerating distributed deep learning with communication scheduling","author":"hashemi","year":"2018"},{"key":"ref2","first-page":"11080","article-title":"Local sgd with periodic averaging: Tighter analysis and adaptive synchronization","author":"haddadpour","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337828"},{"key":"ref1","article-title":"Don’t use large minibatches, use local sgd","author":"lin","year":"2018"},{"key":"ref20","article-title":"Don’t decay the learning rate, increase the batch size","author":"smith","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"ref21","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","location":"Atlanta, GA, USA","start":{"date-parts":[[2020,12,10]]},"end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09378178.pdf?arnumber=9378178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:45:04Z","timestamp":1656344704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9378178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9378178","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}