{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:03:02Z","timestamp":1776931382833,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","funder":[{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["PRE2022-104134, CEX2021-001148-S, and PID2023-147979NB-C2"],"award-info":[{"award-number":["PRE2022-104134, CEX2021-001148-S, and PID2023-147979NB-C2"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767571","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"2088-2099","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Neural Network Training: Distributed Data-Parallel Approaches"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5634-509X","authenticated-orcid":false,"given":"Fernando","family":"V\u00e1zquez-Novoa","sequence":"first","affiliation":[{"name":"Barcelona Supercomputing Center (BSC), Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4544-955X","authenticated-orcid":false,"given":"Pedro","family":"L\u00f3pez","sequence":"additional","affiliation":[{"name":"Universidad Politecnica de Valencia, Valencia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8581-6284","authenticated-orcid":false,"given":"Jos\u00e9","family":"Flich","sequence":"additional","affiliation":[{"name":"Universidad Politecnica de Valencia, Valencia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2941-5499","authenticated-orcid":false,"given":"Rosa M.","family":"Badia","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center (BSC), Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","series-title":"Proceedings of Machine Learning Research","first-page":"1059","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Brock Andy","year":"2021","unstructured":"Andy Brock, Soham De, Samuel\u00a0L Smith, and Karen Simonyan. 2021. High-Performance Large-Scale Image Recognition Without Normalization. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 1059\u20131071. https:\/\/proceedings.mlr.press\/v139\/brock21a.html"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2019.00018"},{"key":"e_1_3_3_3_4_2","series-title":"(ICML\u201913)","first-page":"III\u20131337\u2013III\u201313","volume-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28","author":"Coates Adam","year":"2013","unstructured":"Adam Coates, Brody Huval, Tao Wang, David\u00a0J. Wu, Andrew\u00a0Y. Ng, and Bryan Catanzaro. 2013. Deep learning with COTS HPC systems. In Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 (Atlanta, GA, USA) (ICML\u201913). JMLR.org, III\u20131337\u2013III\u20131345."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Luke\u00a0N Darlow Elliot\u00a0J Crowley Antreas Antoniou and Amos\u00a0J Storkey. 2018. Cinic-10 is not imagenet or cifar-10. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.03505 (2018). 10.48550\/arXiv.1810.03505","DOI":"10.48550\/arXiv.1810.03505"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12948 (2025). 10.48550\/arXiv.2501.12948","DOI":"10.48550\/arXiv.2501.12948"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","unstructured":"Vipul Gupta Santiago\u00a0Akle Serrano and Dennis DeCoste. 2020. Stochastic weight averaging in parallel: Large-batch training that generalizes well. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.02312 (2020). 10.48550\/arXiv.2001.02312","DOI":"10.48550\/arXiv.2001.02312"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Aaron Harlap Deepak Narayanan Amar Phanishayee Vivek Seshadri Nikhil Devanur Greg Ganger and Phil Gibbons. 2018. Pipedream: Fast and efficient pipeline parallel dnn training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.03377 (2018). 10.48550\/arXiv.1806.03377","DOI":"10.48550\/arXiv.1806.03377"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Sagar Imambi Kolla\u00a0Bhanu Prakash and GR Kanagachidambaresan. 2021. PyTorch. Programming with TensorFlow: solution for edge computing applications (2021) 87\u2013104.","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","unstructured":"Pavel Izmailov Dmitrii Podoprikhin Timur Garipov Dmitry Vetrov and Andrew\u00a0Gordon Wilson. 2018. Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.05407 (2018). 10.48550\/arXiv.1803.05407","DOI":"10.48550\/arXiv.1803.05407"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1404.5997 (2014). 10.48550\/arXiv.1404.5997","DOI":"10.48550\/arXiv.1404.5997"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","unstructured":"Shen Li Yanli Zhao Rohan Varma Omkar Salpekar Pieter Noordhuis Teng Li Adam Paszke Jeff Smith Brian Vaughan Pritam Damania et\u00a0al. [n. d.]. PyTorch Distributed: Experiences on Accelerating Data Parallel Training. Proceedings of the VLDB Endowment 13 12 ([n. d.]). 10.14778\/3415478.3415530","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","unstructured":"Tianyang Lin Yuxin Wang Xiangyang Liu and Xipeng Qiu. 2022. A survey of transformers. AI open 3 (2022) 111\u2013132. 10.1016\/j.aiopen.2022.10.001","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Francesc Lordan Rosa\u00a0M. Badia et\u00a0al. 2014. ServiceSs: an interoperable programming framework for the Cloud. Journal of Grid Computing 12 1 (3 2014) 67\u201391. 10.1007\/s10723-013-9272-5","DOI":"10.1007\/s10723-013-9272-5"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Herbert Robbins and Sutton Monro. 1951. A stochastic approximation method. The annals of mathematical statistics (1951) 400\u2013407.","DOI":"10.1214\/aoms\/1177729586"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Otilio Rojas Marisol Monterrubio-Velasco Juan\u00a0E Rodr\u00edguez Scott Callaghan Claudia Abril Benedikt Halldorsson Milad Kowsari Farnaz Bayat Kim\u00a0B Olsen Alice-Agnes Gabriel et\u00a0al. 2025. Earthquake Fault Rupture Modeling and Ground-Motion Simulations for the Southwest Iceland Transform Zone Using CyberShake. Bulletin of the Seismological Society of America 115 1 (2025) 69\u201385. 10.1785\/0120240064","DOI":"10.1785\/0120240064"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Frank Rosenblatt. 1962. Principles of neurodynamics. Perceptrons and the theory of brain mechanisms (1962).","DOI":"10.21236\/AD0256582"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","unstructured":"Alexander Sergeev and M\u00a0Horovod Del\u00a0Balso. 2018. fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1802.05799 10 (2018). 10.48550\/arXiv.1802.05799","DOI":"10.48550\/arXiv.1802.05799"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Enric Tejedor Yolanda Becerra Guillem Alomar Anna Queralt Rosa\u00a0M Badia Jordi Torres Toni Cortes and Jes\u00fas Labarta. 2017. PyCOMPSs: Parallel computational workflows in Python. The International Journal of High Performance Computing Applications 31 1 (2017) 66\u201382. 10.1177\/1094342015594678","DOI":"10.1177\/1094342015594678"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2834892.2834897"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Rikiya Yamashita Mizuho Nishio Richard Kinh\u00a0Gian Do and Kaori Togashi. 2018. Convolutional neural networks: an overview and application in radiology. Insights into imaging 9 (2018) 611\u2013629. 10.1007\/s13244-018-0639-9","DOI":"10.1007\/s13244-018-0639-9"},{"key":"e_1_3_3_3_22_2","unstructured":"Hao Zhang Yuan Li Zhijie Deng Xiaodan Liang Lawrence Carin and Eric Xing. 2020. Autosync: Learning to synchronize for data-parallel distributed deep learning. Advances in Neural Information Processing Systems 33 (2020) 906\u2013917."}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:29:15Z","timestamp":1767986955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":21,"alternative-id":["10.1145\/3731599.3767571","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767571","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}