{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:05:22Z","timestamp":1783577122000,"version":"3.55.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/infocom.2018.8486422","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T18:45:36Z","timestamp":1539888336000},"page":"495-503","source":"Crossref","is-referenced-by-count":100,"title":["Online Job Scheduling in Distributed Machine Learning Clusters"],"prefix":"10.1109","author":[{"given":"Yixin","family":"Bao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanghua","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"ref32","author":"bao","year":"2017","journal-title":"Online Job Scheduling in Distributed Machine Learning Clusters"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/0400000024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"ref36","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"2015","journal-title":"Proc of ICML"},{"key":"ref35","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HPDC.2004.1323519"},{"key":"ref10","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref11","article-title":"Large-Scale Cluster Management at Google with Borg","author":"verma","year":"2015","journal-title":"Proc of ACM EuroSys"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref13","article-title":"Spark: Cluster Computing with Working Sets","author":"zaharia","year":"2010","journal-title":"Proc of USENIX HotCloud"},{"key":"ref14","article-title":"Dominant Resource Fairness: Fair Allocation of Multiple Resource Types","author":"ghodsi","year":"2011","journal-title":"Proc of USENIX NSDI"},{"key":"ref15","article-title":"Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center","author":"hindman","year":"2011","journal-title":"Proc of USENIX NSDI"},{"key":"ref16","year":"0","journal-title":"Kubernetes"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2017.7947053"},{"key":"ref18","article-title":"Dolphin: Runtime Optimization for Distributed Machine Learning","author":"lee","year":"2016","journal-title":"Proc of ICML ML Systems Workshop"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783270"},{"key":"ref28","year":"0","journal-title":"Amazon EC2 Instances"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","article-title":"TetriSched: Global Rescheduling with Adaptive Plan-ahead in Dynamic Heterogeneous Clusters","author":"tumanov","year":"2016","journal-title":"Proc of ACM EuroSys"},{"key":"ref3","year":"0","journal-title":"Paddlepaddle"},{"key":"ref6","article-title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","author":"chen","year":"2016","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in NIPS"},{"key":"ref29","year":"0","journal-title":"Apache Hadoop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"key":"ref8","article-title":"Project Adam: Building an Efficient and Scalable Deep Learning Training System","author":"chilimbi","year":"2014","journal-title":"Proc of USENIX OSDI"},{"key":"ref7","article-title":"Scaling Distributed Machine Learning with the Parameter Server","author":"li","year":"2014","journal-title":"Proc of USENIX OSDI"},{"key":"ref2","year":"0","journal-title":"The Microsoft Cognitive Toolkit"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","article-title":"TensorFlow: A System for Large-Scale Machine Learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX OSDI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218460"},{"key":"ref22","article-title":"Truthful Online Scheduling with Commitments","author":"azar","year":"2015","journal-title":"Proc of ACM EC"},{"key":"ref21","article-title":"Scheduling Jobs across Geo-Distributed Data-centers with Max-Min Fairness","author":"chen","year":"2017","journal-title":"Proc of IEEE INFOCOM"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2609844"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2486159.2486187"},{"key":"ref26","article-title":"Automatic Scaling of Internet Applications for Cloud Computing Services","author":"xiao","year":"2014","journal-title":"IEEE Transactions on Computers"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/2745844.2745855","article-title":"Online Auctions in IaaS Clouds: Welfare and Profit Maximization with Server Costs","author":"zhang","year":"2015","journal-title":"Proc of ACM SIGMETRICS"}],"event":{"name":"IEEE INFOCOM 2018 - IEEE Conference on Computer Communications","location":"Honolulu, HI","start":{"date-parts":[[2018,4,16]]},"end":{"date-parts":[[2018,4,19]]}},"container-title":["IEEE INFOCOM 2018 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8464035\/8485803\/08486422.pdf?arnumber=8486422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T19:18:37Z","timestamp":1643224717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8486422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/infocom.2018.8486422","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}