{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T10:59:28Z","timestamp":1777546768580,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SHF-1816850"],"award-info":[{"award-number":["SHF-1816850"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,5,1]]},"DOI":"10.1109\/tpds.2021.3104242","type":"journal-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T19:54:07Z","timestamp":1628711647000},"page":"1128-1143","source":"Crossref","is-referenced-by-count":17,"title":["Elastic Parameter Server: Accelerating ML Training With Scalable Resource Scheduling"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8187-779X","authenticated-orcid":false,"given":"Shaoqi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aidi","family":"Pi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0466-7609","authenticated-orcid":false,"given":"Xiaobo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5055","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303957"},{"key":"ref33","year":"0"},{"key":"ref32","first-page":"631","article-title":"LITZ: Elastic framework for high-performance distributed machine learning","author":"qiao","year":"2018","journal-title":"Proc Conf USENIX Annu Tech Conf"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref30","first-page":"571","article-title":"Project Adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref36","first-page":"412","article-title":"Distributed hierarchical GPU parameter server for massive scale deep learning ads systems","author":"zhao","year":"2020","journal-title":"Proc MLSys Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref34","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","author":"hashemi","year":"2019","journal-title":"Proc SysML Conf"},{"key":"ref28","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref27","first-page":"349","article-title":"Yak: A high-performance big-data-friendly garbage collector","author":"nguyen","year":"2016","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3274808.3274828"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196892"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177734"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098029"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref24","first-page":"412","article-title":"Distributed hierarchical GPU parameter server for massive scale deep learning ADS systems","author":"zhao","year":"2020","journal-title":"Proc MLSys Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3365109.3368788"},{"key":"ref26","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref50","article-title":"Population based training of neural networks","author":"jaderberg","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2723872.2723882"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.02.022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.03.001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3148149"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267838"},{"key":"ref52","first-page":"251","article-title":"Preemptive, low latency datacenter scheduling via lightweight virtualization","author":"chen","year":"2017","journal-title":"Proc Conf USENIX Annu Tech Conf"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1749-4699\/8\/1\/014008"},{"key":"ref11","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"li","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref40","first-page":"11450","article-title":"Communication-efficient distributed blockwise momentum SGD with error-feedback","author":"zheng","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135994"},{"key":"ref13","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref14","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc Conf USENIX Annu Tech Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref16","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","author":"jayarajan","year":"2019","journal-title":"Proc SysML Conf"},{"key":"ref17","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","author":"hsieh","year":"2017","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015289"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670984"},{"key":"ref3","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref6","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref8","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","author":"hindman","year":"2011","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3361525.3361538"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421307"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183760"},{"key":"ref48","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"2019","journal-title":"Proc Conf USENIX Annu Tech Conf"},{"key":"ref47","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref42","first-page":"400","article-title":"Resource elasticity in distributed deep learning","author":"or","year":"2020","journal-title":"Proc MLSys Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749432"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064182"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9578942\/9511790-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9578942\/09511790.pdf?arnumber=9511790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:45Z","timestamp":1649443725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9511790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,1]]},"references-count":56,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3104242","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,1]]}}}