{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:17:33Z","timestamp":1730279853996,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"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":[[2023,7]]},"DOI":"10.1109\/jcc59055.2023.00006","type":"proceedings-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T17:30:29Z","timestamp":1693503029000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["OLM<sup>2<\/sup>: Automatic Optimal Strategy Generating for Large-Scale Model Training with Limited-Memory"],"prefix":"10.1109","author":[{"given":"Zhilin","family":"Yang","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,National Key Laboratory of Parallel and Distributed Computing,Changsha 410073,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,National Key Laboratory of Parallel and Distributed Computing,Changsha 410073,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linbo","family":"Qiao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,National Key Laboratory of Parallel and Distributed Computing,Changsha 410073,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,National Key Laboratory of Parallel and Distributed Computing,Changsha 410073,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,National Key Laboratory of Parallel and Distributed Computing,Changsha 410073,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00030"},{"key":"ref2","article-title":"A neural probabilistic language model","volume":"13","author":"Bengio","year":"2000","journal-title":"Advances in neural information processing systems"},{"article-title":"Training deep nets with sublinear memory cost","year":"2016","author":"Chen","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref5","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2021","journal-title":"J. Mach. Learn. Res"},{"volume-title":"Gurobi optimization","year":"2023","key":"ref6"},{"key":"ref7","article-title":"Memory-efficient backpropagation through time","volume":"29","author":"Gruslys","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378530"},{"key":"ref10","first-page":"497","article-title":"Checkmate: Breaking the memory wall with optimal tensor rematerialization","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Jain"},{"article-title":"Dynamic tensor rematerialization","volume-title":"International Conference on Learning Representations","author":"Kirisame","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3247001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3315573.3329984"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"M6: A chinese multimodal pretrainer","year":"2021","author":"Lin","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref18"},{"issue":"1","key":"ref19","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00057"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Simonyan","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010067"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"}],"event":{"name":"2023 IEEE International Conference on Joint Cloud Computing (JCC)","start":{"date-parts":[[2023,7,17]]},"location":"Athens, Greece","end":{"date-parts":[[2023,7,20]]}},"container-title":["2023 IEEE International Conference on Joint Cloud Computing (JCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10227855\/10229517\/10229720.pdf?arnumber=10229720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T22:03:02Z","timestamp":1709330582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10229720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/jcc59055.2023.00006","relation":{},"subject":[],"published":{"date-parts":[[2023,7]]}}}