{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:27:09Z","timestamp":1778081229790,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"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":[[2023,6,19]]},"DOI":"10.1109\/iwqos57198.2023.10188717","type":"proceedings-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T17:21:00Z","timestamp":1690478460000},"page":"1-10","source":"Crossref","is-referenced-by-count":5,"title":["spotDNN: Provisioning Spot Instances for Predictable Distributed DNN Training in the Cloud"],"prefix":"10.1109","author":[{"given":"Ruitao","family":"Shang","sequence":"first","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Xu","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoyan","family":"Bai","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Louisiana at Lafayette"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangming","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Peng Cheng Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3561074.3561082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392671"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3134644"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00029"},{"key":"ref15","first-page":"1","article-title":"Large scale distributed deep networks","author":"dean","year":"0","journal-title":"Proc of NIPS"},{"key":"ref37","first-page":"1","article-title":"Spotnik: Designing distributed machine learning for transient cloud resources","author":"wagenlander","year":"0","journal-title":"Proc of USENIX HotCloud"},{"key":"ref14","first-page":"833","article-title":"SRIFTY: Swift and Thrifty Distributed Neural Network Training on the Cloud","author":"luo","year":"0","journal-title":"Proc of MLSys"},{"key":"ref36","author":"thorpe","year":"2022","journal-title":"Bamboo Making preemptible instances resilient for affordable training of large dnns"},{"key":"ref31","first-page":"503","article-title":"Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","author":"geoffrey","year":"0","journal-title":"Proc of USENIX ATC"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3054656"},{"key":"ref11","first-page":"1","article-title":"Accelerating Distributed Learning in Non-Dedicated Environments","volume":"preprint","author":"chen","year":"2021","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref10","first-page":"481","article-title":"Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads","author":"narayanan","year":"0","journal-title":"Proc of USENIX OSDI"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3358960.3379141"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563499"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337873"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"University of Toronto Toronto Ontario Canada Tech Rep"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref18","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc of ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref23","author":"seber","year":"2012","journal-title":"Linear Regression Analysis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref25","first-page":"265","article-title":"TensorFlow: a system for Large-Scale machine learning","author":"abadi","year":"0","journal-title":"Proc of USENIX OSDI"},{"key":"ref20","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"0","journal-title":"Proc of NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref21","first-page":"1","article-title":"Revisiting distributed synchronous SGD","author":"chen","year":"2016","journal-title":"Proc of ICLR Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064182"},{"key":"ref27","author":"chaumond","year":"2020","journal-title":"How to train a new language model from scratch using Transformers and Tokenizers"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-019-02912-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2019.00024"},{"key":"ref9","first-page":"1","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"0","journal-title":"Proc of NIPS"},{"key":"ref4","first-page":"203","article-title":"CheckFreq: Frequent, Fine-Grained DNN Checkpointing","author":"mohan","year":"0","journal-title":"Proc of USENIX FAST"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2873397"},{"key":"ref6","article-title":"Amazon","year":"2023","journal-title":"Amazon EC2 Spot Instances"},{"key":"ref5","first-page":"1","article-title":"Analysis and exploitation of dynamic pricing in the public cloud for ml training","author":"narayanan","year":"2020","journal-title":"Proc of VLDB Workshop"}],"event":{"name":"2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS)","location":"Orlando, FL, USA","start":{"date-parts":[[2023,6,19]]},"end":{"date-parts":[[2023,6,21]]}},"container-title":["2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10188660\/10188690\/10188717.pdf?arnumber=10188717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:38:49Z","timestamp":1692034729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10188717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iwqos57198.2023.10188717","relation":{},"subject":[],"published":{"date-parts":[[2023,6,19]]}}}