{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:12:30Z","timestamp":1769829150106,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053834","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"8871-8875","source":"Crossref","is-referenced-by-count":27,"title":["Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD"],"prefix":"10.1109","author":[{"given":"Jianyu","family":"Wang","sequence":"first","affiliation":[]},{"given":"Hao","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Gauri","family":"Joshi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Local SGD converges fast and communicates little","author":"stich","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref12","article-title":"Cooperative SGD: A unified framework for the design and analysis of communication- efficient SGD algorithms","author":"wang","year":"2018"},{"key":"ref13","first-page":"1273","article-title":"Communication- efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref14","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local- update SGD","volume":"abs 1810 8313","author":"wang","year":"2018","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"key":"ref16","article-title":"Stochastic gradient push for distributed deep learning","author":"assran","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref17","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","author":"wang","year":"2019"},{"key":"ref19","first-page":"685","article-title":"Deep learning with elastic averaged SGD","author":"zhang","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref6","first-page":"803","article-title":"Slow and stale gradients can win the race: Error-runtime trade-offs in distributed SGD","author":"dutta","year":"2018","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref5","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","author":"vogels","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2952051"},{"key":"ref7","article-title":"Anytime minibatch: Exploiting stragglers in online distributed optimization","author":"ferdinand","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref2","article-title":"Language models are unsupervised multi-task learners","author":"radford","year":"2019","journal-title":"Open AI tech report"},{"key":"ref1","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-2122-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/637"},{"key":"ref22","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Cifar-10 (canadian institute for advanced research)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337828"},{"key":"ref24","article-title":"Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration","author":"paszke","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053834.pdf?arnumber=9053834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:27:02Z","timestamp":1656376022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053834","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}