{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:27:08Z","timestamp":1778081228114,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100007059","name":"Northwestern University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007059","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004344","name":"Adobe Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004344","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12,6]]},"DOI":"10.1145\/3492323.3495594","type":"proceedings-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T18:36:51Z","timestamp":1644259011000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Scheduling ML training on unreliable spot instances"],"prefix":"10.1145","author":[{"given":"Sheng","family":"Yang","sequence":"first","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samir","family":"Khuller","sequence":"additional","affiliation":[{"name":"Northwestern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunav","family":"Choudhary","sequence":"additional","affiliation":[{"name":"Adobe Research, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subrata","family":"Mitra","sequence":"additional","affiliation":[{"name":"Adobe Research, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanak","family":"Mahadik","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,7]]},"reference":[{"key":"e_1_3_2_1_1_1","series-title":"SIAM Rev. 60, 2","volume-title":"Optimization Methods for Large-Scale Machine Learning","author":"Curtis Frank E.","year":"2018","unstructured":"L\u00e9on. Bottou, Frank E. Curtis, and Jorge. Nocedal. 2018. Optimization Methods for Large-Scale Machine Learning. SIAM Rev. 60, 2 (2018)."},{"key":"e_1_3_2_1_2_1","first-page":"4","volume":"33","author":"Dean Brian C","year":"2008","unstructured":"Brian C Dean, Michel X Goemans, and Jan Vondr\u00e1k. 2008. Approximating the stochastic knapsack problem: The benefit of adaptivity. Mathematics of Operations Research 33, 4 (2008).","journal-title":"Operations Research"},{"key":"e_1_3_2_1_3_1","volume-title":"Approximation algorithms for correlated knapsacks and non-martingale bandits","author":"Gupta Anupam","unstructured":"Anupam Gupta, Ravishankar Krishnaswamy, Marco Molinaro, and Ramamoorthi Ravi. 2011. Approximation algorithms for correlated knapsacks and non-martingale bandits. In FOCS. IEEE."},{"key":"e_1_3_2_1_4_1","volume-title":"Scheduling to minimize average completion time: Off-line and on-line approximation algorithms. Mathematics of operations research 22, 3","author":"Hall Leslie A","year":"1997","unstructured":"Leslie A Hall, Andreas S Schulz, David B Shmoys, and Joel Wein. 1997. Scheduling to minimize average completion time: Off-line and on-line approximation algorithms. Mathematics of operations research 22, 3 (1997)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Aaron Harlap Alexey Tumanov Andrew Chung Gregory R Ganger and Phillip B Gibbons. 2017. Proteus: agile ml elasticity through tiered reliability in dynamic resource markets. In EuroSys. ACM.","DOI":"10.1145\/3064176.3064182"},{"key":"e_1_3_2_1_6_1","unstructured":"Myeongjae Jeon Shivaram Venkataraman Junjie Qian Amar Phanishayee Wencong Xiao and Fan Yang. 2018. Multi-tenant GPU clusters for deep learning workloads: Analysis and implications. Technical Report. Microsoft Research."},{"key":"e_1_3_2_1_7_1","series-title":"SIAM J. Comput. 30, 1","volume-title":"Allocating bandwidth for bursty connections","author":"Kleinberg Jon","year":"2000","unstructured":"Jon Kleinberg, Yuval Rabani, and \u00c9va Tardos. 2000. Allocating bandwidth for bursty connections. SIAM J. Comput. 30, 1 (2000)."},{"key":"e_1_3_2_1_8_1","volume":"201","author":"Niu Feng","unstructured":"Feng Niu, Benjamin Recht, Christopher Re, and Stephen J. Wright. 2011. HOG-WILD! A Lock-Free Approach to Parallelizing Stochastic Gradient Descent. In NIPS (Granada, Spain) (NIPS'11). Curran Associates Inc., Red Hook, NY, USA, 693--701.","journal-title":"Stephen J. Wright."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Yanghua Peng Yixin Bao Yangrui Chen Chuan Wu and Chuanxiong Guo. 2018. Optimus: an efficient dynamic resource scheduler for deep learning clusters. In EuroSys. ACM.","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_10_1","volume-title":"Load Prediction and Hot Spot Detection Models for Autonomic Cloud Computing","author":"Saripalli Prasad","unstructured":"Prasad Saripalli, G. V. R. Kiran, R. Ravi Shankar, Harish Narware, and Nitin Bindal. 2011. Load Prediction and Hot Spot Detection Models for Autonomic Cloud Computing. In UCC. IEEE Computer Society."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078505.3078511"},{"key":"e_1_3_2_1_12_1","volume-title":"Curran Associates","author":"Xu Pan","unstructured":"Pan Xu, Jinghui Chen, Difan Zou, and Quanquan Gu. 2018. Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization. In NIPS, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.). Curran Associates, Inc."},{"key":"e_1_3_2_1_13_1","volume":"201","author":"Zhang Haoyu","unstructured":"Haoyu Zhang, Logan Stafman, Andrew Or, and Michael J Freedman. 2017. Slaq: quality-driven scheduling for distributed machine learning. In SoCC. ACM.","journal-title":"Michael J Freedman."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Xiaoxi Zhang Jianyu Wang Gauri Joshi and Carlee Joe-Wong. 2020. Machine Learning on Volatile Instances. In INFOCOM.","DOI":"10.1109\/INFOCOM41043.2020.9155448"}],"event":{"name":"UCC '21: 2021 IEEE\/ACM 14th International Conference on Utility and Cloud Computing","location":"Leicester United Kingdom","acronym":"UCC '21","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE TCSC IEEE Technical Committee on Scalable Computing"]},"container-title":["Proceedings of the 14th IEEE\/ACM International Conference on Utility and Cloud Computing Companion"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3492323.3495594","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3492323.3495594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T23:22:32Z","timestamp":1763421752000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3492323.3495594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,6]]},"references-count":14,"alternative-id":["10.1145\/3492323.3495594","10.1145\/3492323"],"URL":"https:\/\/doi.org\/10.1145\/3492323.3495594","relation":{},"subject":[],"published":{"date-parts":[[2021,12,6]]},"assertion":[{"value":"2022-02-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}