{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:58:11Z","timestamp":1773377891320,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,26]],"date-time":"2022-06-26T00:00:00Z","timestamp":1656201600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,26]],"date-time":"2022-06-26T00:00:00Z","timestamp":1656201600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,26]]},"DOI":"10.1109\/isit50566.2022.9834752","type":"proceedings-article","created":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T15:34:22Z","timestamp":1659540862000},"page":"2996-3000","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Worker Grouping for Communication-Efficient and Straggler-Tolerant Distributed SGD"],"prefix":"10.1109","author":[{"given":"Feng","family":"Zhu","sequence":"first","affiliation":[{"name":"Fudan University,Department of Communication Science and Engineering,Shanghai,China,200433"}]},{"given":"Jingjing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University,Department of Communication Science and Engineering,Shanghai,China,200433"}]},{"given":"Osvaldo","family":"Simeone","sequence":"additional","affiliation":[{"name":"King’s College London,Department of Informatics,London,U.K.,WC2R 2LS"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University,Department of Communication Science and Engineering,Shanghai,China,200433"}]}],"member":"263","reference":[{"key":"ref10","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref11","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","author":"le roux","year":"2012","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref12","article-title":"Stochastic dual coordinate ascent methods for regularized loss minimization","volume":"14","author":"shalev-shwartz","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref15","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc Int Conf on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2019.8755563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2756959"},{"key":"ref19","first-page":"5610","article-title":"Communication-computation efficient gradient coding","author":"ye","year":"2018","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2124295.2124312"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref6","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume":"27","author":"li","year":"2014","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref5","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref8","first-page":"5055","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"2018","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref7","first-page":"3368","article-title":"Gradient coding: Avoiding stragglers in distributed learning","volume":"70","author":"tandon","year":"2017","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref2","first-page":"4427","article-title":"Federated multi-task learning","author":"smith","year":"2017","journal-title":"Proc of Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref1","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref20","article-title":"Erasurehead: Distributed gradient descent without delays using approximate gradient coding","volume":"arxiv 1901 9671","author":"wang","year":"2019"},{"key":"ref22","first-page":"1","article-title":"LAGC: Lazily aggregated gradient coding for straggler-tolerant and communication-efficient distributed learning","author":"zhang","year":"2020","journal-title":"IEEE Trans Neural Networks and Learning Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991361"},{"key":"ref24","first-page":"613","article-title":"CADA: Communication-adaptive distributed Adam","author":"chen","year":"2021","journal-title":"Proc Int Conf on Artificial Intelligence and Statistics"},{"key":"ref23","article-title":"LASG: Lazily aggregated stochastic gradients for communication-efficient distributed learning","volume":"arxiv 2002 11360","author":"chen","year":"2020"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3366706","article-title":"Rateless codes for near-perfect load balancing in distributed matrixvector multiplication","volume":"3","author":"mallick","year":"2019","journal-title":"Proc ACM on Measurement and Analysis of Computing Systems"}],"event":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","location":"Espoo, Finland","start":{"date-parts":[[2022,6,26]]},"end":{"date-parts":[[2022,7,1]]}},"container-title":["2022 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9834325\/9834269\/09834752.pdf?arnumber=9834752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:29Z","timestamp":1773347729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9834752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,26]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/isit50566.2022.9834752","relation":{},"subject":[],"published":{"date-parts":[[2022,6,26]]}}}