{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:56:25Z","timestamp":1775854585948,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:00:00Z","timestamp":1708387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1145\/3627535.3638505","type":"proceedings-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T14:22:41Z","timestamp":1708438961000},"page":"257-269","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Training one DeePMD Model in Minutes: a Step towards Online Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6085-4645","authenticated-orcid":false,"given":"Siyu","family":"Hu","sequence":"first","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2511-0172","authenticated-orcid":false,"given":"Tong","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0990-9515","authenticated-orcid":false,"given":"Qiuchen","family":"Sha","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7643-3392","authenticated-orcid":false,"given":"Enji","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5696-3090","authenticated-orcid":false,"given":"Xiangyu","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Qingdao Institute of Software, China University of Petroleum, Qingdao, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7306-4118","authenticated-orcid":false,"given":"Liping","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7061-2692","authenticated-orcid":false,"given":"Lin-Wang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6361-5948","authenticated-orcid":false,"given":"Guangming","family":"Tan","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8539-8326","authenticated-orcid":false,"given":"Weile","family":"Jia","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. {TensorFlow}: a system for {Large-Scale} machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/0013-7944(84)90096-1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29939-5"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/26\/18\/183001"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/anie.201703114"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401"},{"key":"e_1_3_2_1_7_1","volume-title":"Silicon liquid structure and crystal nucleation from ab initio deep metadynamics. Physical review letters 121, 26","author":"Bonati Luigi","year":"2018","unstructured":"Luigi Bonati and Michele Parrinello. 2018. Silicon liquid structure and crystal nucleation from ab initio deep metadynamics. Physical review letters 121, 26 (2018), 265701."},{"key":"e_1_3_2_1_8_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et al. 2018. TVM: An automated End-to-End optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 578--594."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0894-0347-08-00610-3"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108156"},{"key":"e_1_3_2_1_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.014104"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Patrick L Fitzgibbons David L Page Donald Weaver Ann D Thor D Craig Allred Gary M Clark Stephen G Ruby Frances O'Malley Jean F Simpson James L Connolly et al. 2000. Prognostic factors in breast cancer: College of American Pathologists consensus statement 1999. Archives of pathology & laboratory medicine 124 7 (2000) 966--978.","DOI":"10.5858\/2000-124-0966-PFIBC"},{"key":"e_1_3_2_1_14_1","volume-title":"Matthew James Johnson, and Chris Leary","author":"Frostig Roy","year":"2018","unstructured":"Roy Frostig, Matthew James Johnson, and Chris Leary. 2018. Compiling machine learning programs via high-level tracing. Systems for Machine Learning 4, 9 (2018)."},{"key":"e_1_3_2_1_15_1","volume-title":"Reactive uptake of N2O5 by atmospheric aerosol is dominated by interfacial processes. Science 371, 6532","author":"Galib Mirza","year":"2021","unstructured":"Mirza Galib and David T Limmer. 2021. Reactive uptake of N2O5 by atmospheric aerosol is dominated by interfacial processes. Science 371, 6532 (2021), 921--925."},{"key":"e_1_3_2_1_16_1","volume-title":"Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules. In Machine Learning for Molecules Workshop, NeurIPS.","author":"Gasteiger Johannes","year":"2020","unstructured":"Johannes Gasteiger, Shankari Giri, Johannes T. Margraf, and Stephan G\u00fcnnemann. 2020. Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules. In Machine Learning for Molecules Workshop, NeurIPS."},{"key":"e_1_3_2_1_17_1","volume-title":"Directional Message Passing for Molecular Graphs. In International Conference on Learning Representations (ICLR).","author":"Gasteiger Johannes","year":"2020","unstructured":"Johannes Gasteiger, Janek Gro\u00df, and Stephan G\u00fcnnemann. 2020. Directional Message Passing for Molecular Graphs. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_18_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508425"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Gupta Vineet","year":"2018","unstructured":"Vineet Gupta, Tomer Koren, and Yoram Singer. 2018. Shampoo: Preconditioned stochastic tensor optimization. In International Conference on Machine Learning. PMLR, 1842--1850."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","unstructured":"Elad Hoffer Itay Hubara and Daniel Soudry. 2018. Train longer generalize better: closing the generalization gap in large batch training of neural networks. arXiv:1705.08741 [stat.ML]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25957"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/cjoc.202100456"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2013.05.005"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00009"},{"key":"e_1_3_2_1_27_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"XLA: TensorFlow, compiled. TensorFlow Dev Summit 2, 3","author":"Leary Chris","year":"2017","unstructured":"Chris Leary and Todd Wang. 2017. XLA: TensorFlow, compiled. TensorFlow Dev Summit 2, 3 (2017)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2019.04.014"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3030548"},{"key":"e_1_3_2_1_31_1","volume-title":"On the limited memory BFGS method for large scale optimization. Mathematical programming 45, 1--3","author":"Liu Dong C","year":"1989","unstructured":"Dong C Liu and Jorge Nocedal. 1989. On the limited memory BFGS method for large scale optimization. Mathematical programming 45, 1--3 (1989), 503--528."},{"key":"e_1_3_2_1_32_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-021-00559-9"},{"key":"e_1_3_2_1_34_1","first-page":"e1900031","article-title":"Simulating diffusion properties of solid-state electrolytes via a neural network potential: performance and training scheme","volume":"2","author":"Marcolongo Aris","year":"2020","unstructured":"Aris Marcolongo, Tobias Binninger, Federico Zipoli, and Teodoro Laino. 2020. Simulating diffusion properties of solid-state electrolytes via a neural network potential: performance and training scheme. Chem-SystemsChem 2, 3 (2020), e1900031.","journal-title":"Chem-SystemsChem"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 2408--2417","author":"Martens James","year":"2015","unstructured":"James Martens and Roger Grosse. 2015. Optimizing neural networks with kronecker-factored approximate curvature. In International conference on machine learning. PMLR, 2408--2417."},{"key":"e_1_3_2_1_36_1","volume-title":"Numerical Optimization","author":"Mikosch Thomas V","year":"2006","unstructured":"Thomas V Mikosch, Sidney I Resnick, and Stephen M Robinson. 2006. Numerical Optimization (2nd Edition). (2006).","edition":"2"},{"key":"e_1_3_2_1_37_1","unstructured":"Jorge Nocedal\u00a7. 2016. Optimization Methods for Large-Scale Machine Learning."},{"key":"e_1_3_2_1_38_1","volume-title":"Phase transition dynamics","author":"Onuki Akira","unstructured":"Akira Onuki. 2002. Phase transition dynamics. Cambridge University Press."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004354"},{"key":"e_1_3_2_1_40_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_41_1","volume-title":"Growth of carbon nanotubes on metal nanoparticles: a microscopic mechanism from ab initio molecular dynamics simulations. Physical review letters 95, 9","author":"Raty Jean-Yves","year":"2005","unstructured":"Jean-Yves Raty, Fran\u00e7ois Gygi, and Giulia Galli. 2005. Growth of carbon nanotubes on metal nanoparticles: a microscopic mechanism from ab initio molecular dynamics simulations. Physical review letters 95, 9 (2005), 096103."},{"key":"e_1_3_2_1_42_1","volume-title":"Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Robert M\u00fcller.","author":"Sch\u00fctt Kristof","year":"2017","unstructured":"Kristof Sch\u00fctt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Robert M\u00fcller. 2017. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_43_1","unstructured":"Hao-Jun Michael Shi Tsung-Hsien Lee Shintaro Iwasaki Jose Gallego-Posada Zhijing Li Kaushik Rangadurai Dheevatsa Mudigere and Michael Rabbat. 2023. A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale. arXiv:2309.06497 [cs.LG]"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2014.12.018"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27504-0"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2018.03.016"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.103.024108"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpclett.7b01072"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17275"},{"key":"e_1_3_2_1_50_1","volume-title":"Scaling sgd batch size to 32k for imagenet training. arXiv preprint arXiv:1708.03888 6, 12","author":"You Yang","year":"2017","unstructured":"Yang You, Igor Gitman, and Boris Ginsburg. 2017. Scaling sgd batch size to 32k for imagenet training. arXiv preprint arXiv:1708.03888 6, 12 (2017), 6."},{"key":"e_1_3_2_1_51_1","volume-title":"Large batch optimization for deep learning: Training bert in 76 minutes. arXiv preprint arXiv:1904.00962","author":"You Yang","year":"2019","unstructured":"Yang You, Jing Li, Sashank Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, and Cho-Jui Hsieh. 2019. Large batch optimization for deep learning: Training bert in 76 minutes. arXiv preprint arXiv:1904.00962 (2019)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.126.236001"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07007-9"},{"key":"e_1_3_2_1_54_1","volume-title":"Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on mathematical software (TOMS) 23, 4","author":"Zhu Ciyou","year":"1997","unstructured":"Ciyou Zhu, Richard H Byrd, Peihuang Lu, and Jorge Nocedal. 1997. Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on mathematical software (TOMS) 23, 4 (1997), 550--560."}],"event":{"name":"PPoPP '24: 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Edinburgh United Kingdom","acronym":"PPoPP '24","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638505","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627535.3638505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:04Z","timestamp":1750287004000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,20]]},"references-count":54,"alternative-id":["10.1145\/3627535.3638505","10.1145\/3627535"],"URL":"https:\/\/doi.org\/10.1145\/3627535.3638505","relation":{},"subject":[],"published":{"date-parts":[[2024,2,20]]},"assertion":[{"value":"2024-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}