{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:15:25Z","timestamp":1730247325534,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222032","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"2395-2399","source":"Crossref","is-referenced-by-count":0,"title":["Locally Accumulated Adam For Distributed Training With Sparse Updates"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Chen","sequence":"first","affiliation":[{"name":"Vrije Universiteit Brussel (VUB),ETRO Department,Brussels,Belgium,B-1050"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Deligiannis","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Brussel (VUB),ETRO Department,Brussels,Belgium,B-1050"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Image transformer","volume-title":"International Conference on Machine Learning","author":"Parmar","key":"ref4"},{"key":"ref5","first-page":"5463","article-title":"End-to-end object detection with transformers","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Carion"},{"article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"International Conference on Learning Representations","author":"Mehta","key":"ref6"},{"key":"ref7","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"CoRR"},{"article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Lin","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084806"},{"key":"ref10","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","author":"Alistarh","year":"2016","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume":"31","author":"Wangni","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"1-bit adam: Communication efficient large-scale training with adam\u2019s convergence speed","volume-title":"International Conference on Machine Learning","author":"Tang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3470890"},{"key":"ref16","article-title":"Communication efficient distributed machine learning with the parameter server","author":"Li","year":"2014","journal-title":"NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05587"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2023,10,8]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222032.pdf?arnumber=10222032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:52:59Z","timestamp":1710363179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222032","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}