{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T18:06:40Z","timestamp":1759774000990,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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":[[2021,12]]},"DOI":"10.1109\/globecom46510.2021.9686014","type":"proceedings-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T21:59:04Z","timestamp":1643839144000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["CE-SGD: Communication-Efficient Distributed Machine Learning"],"prefix":"10.1109","author":[{"given":"Zeyi","family":"Tao","sequence":"first","affiliation":[{"name":"William & Mary,Department of Computer Science,Williamsburg,VA,23185"}]},{"given":"Qi","family":"Xia","sequence":"additional","affiliation":[{"name":"William & Mary,Department of Computer Science,Williamsburg,VA,23185"}]},{"given":"Qun","family":"Li","sequence":"additional","affiliation":[{"name":"William & Mary,Department of Computer Science,Williamsburg,VA,23185"}]},{"given":"Songqing","family":"Cheng","sequence":"additional","affiliation":[{"name":"Geroge Mason University,Department of Computer Science,Fairfax,VA,22030"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Scalable distributed dnn training using commodity gpu cloud computing","author":"strom","year":"2015","journal-title":"InterSpeech"},{"journal-title":"Deep Gradient Compression Reducing the Communication Bandwidth for Distributed Training","year":"2020","author":"lin","key":"ref11"},{"key":"ref12","first-page":"3370","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","volume":"32","author":"sun","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553417"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2016.004"},{"key":"ref15","volume":"abs 1704 5021","author":"aji","year":"2017","journal-title":"Sparse Communication for Distributed Gradient Descent"},{"key":"ref4","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1 ser NIPS'12"},{"key":"ref3","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume":"27","author":"li","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","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":"2014 IEEE INTERSPEECH"},{"key":"ref5","article-title":"QSGD: randomized quantization for communication-optimal stochastic gradient descent","volume":"abs 1610 2132","author":"alistarh","year":"2016","journal-title":"CoRR"},{"key":"ref8","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","volume":"abs","author":"zhou","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","volume":"abs 1705 7878","author":"wen","year":"2017","journal-title":"CoRR"},{"key":"ref2","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"NIPS"},{"key":"ref1","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","volume":"24","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"SGD learns over-parameterized networks that provably generalize on linearly separable data","author":"brutzkus","year":"2018","journal-title":"International Conference on Learning Representations"}],"event":{"name":"GLOBECOM 2021 - 2021 IEEE Global Communications Conference","start":{"date-parts":[[2021,12,7]]},"location":"Madrid, Spain","end":{"date-parts":[[2021,12,11]]}},"container-title":["2021 IEEE Global Communications Conference (GLOBECOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9685019\/9685006\/09686014.pdf?arnumber=9686014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T01:11:12Z","timestamp":1670375472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9686014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/globecom46510.2021.9686014","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]}}}