{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:37Z","timestamp":1750220197541,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,17]]},"DOI":"10.1145\/3528416.3530246","type":"proceedings-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T02:16:59Z","timestamp":1651717019000},"page":"181-184","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Orchestra"],"prefix":"10.1145","author":[{"given":"Haizhou","family":"Du","sequence":"first","affiliation":[{"name":"Shanghai University of Electric Power, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai University of Electric Power, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Xiang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,5,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks. In International Conference on Learning Representations.","author":"Castiglia Timothy","year":"2020","unstructured":"Timothy Castiglia, Anirban Das, and Stacy Patterson. 2020. Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","volume-title":"Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981","author":"Chen Jianmin","year":"2016","unstructured":"Jianmin Chen, Xinghao Pan, Rajat Monga, Samy Bengio, and Rafal Jozefowicz. 2016. Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1600"},{"key":"e_1_3_2_1_4_1","unstructured":"Jeffrey Dean Greg Corrado Rajat Monga Kai Chen Matthieu Devin Mark Mao Marc'aurelio Ranzato Andrew Senior Paul Tucker Ke Yang et al. 2012. Large scale distributed deep networks. Advances in neural information processing systems 25 (2012) 1223--1231."},{"key":"e_1_3_2_1_5_1","volume-title":"Short-dot: Computing large linear transforms distributedly using coded short dot products. Advances In Neural Information Processing Systems 29","author":"Dutta Sanghamitra","year":"2016","unstructured":"Sanghamitra Dutta, Viveck Cadambe, and Pulkit Grover. 2016. Short-dot: Computing large linear transforms distributedly using coded short dot products. Advances In Neural Information Processing Systems 29 (2016)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning. PMLR, 1406--1415","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, R\u00e9mi Munos, Karen Simonyan, Volodymyr Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, Shane Legg, and Koray Kavukcuoglu. 2018. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. In Proceedings of the 35th International Conference on Machine Learning. PMLR, 1406--1415."},{"key":"e_1_3_2_1_7_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)."},{"volume-title":"Model Accuracy and Runtime Tradeoff in Distributed Deep Learning: A Systematic Study. In 2016 IEEE 16th International Conference on Data Mining (ICDM). IEEE Computer Society","author":"Gupta S.","key":"e_1_3_2_1_8_1","unstructured":"S. Gupta, W. Zhang, and F. Wang. 2016. Model Accuracy and Runtime Tradeoff in Distributed Deep Learning: A Systematic Study. In 2016 IEEE 16th International Conference on Data Mining (ICDM). IEEE Computer Society, Los Alamitos, CA, USA, 171--180."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","volume-title":"Densenet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869","author":"Iandola Forrest","year":"2014","unstructured":"Forrest Iandola, Matt Moskewicz, Sergey Karayev, Ross Girshick, Trevor Darrell, and Kurt Keutzer. 2014. Densenet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8007058"},{"key":"e_1_3_2_1_12_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. Master's thesis. University of Toronto."},{"key":"e_1_3_2_1_13_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations.","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"e_1_3_2_1_15_1","unstructured":"Ryan McDonald Keith Hall and Gideon Mann. 2010. Distributed training strategies for the structured perceptron. In Human language technologies: The 2010 annual conference of the North American chapter of the association for computational linguistics. 456--464."},{"key":"e_1_3_2_1_16_1","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics. PMLR 1273--1282."},{"key":"e_1_3_2_1_17_1","volume-title":"Local SGD converges fast and communicates little. arXiv preprint arXiv:1805.09767","author":"Stich Sebastian U","year":"2018","unstructured":"Sebastian U Stich. 2018. Local SGD converges fast and communicates little. arXiv preprint arXiv:1805.09767 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 7174--7183","author":"Yu Hao","year":"2019","unstructured":"Hao Yu and Rong Jin. 2019. On the computation and communication complexity of parallel sgd with dynamic batch sizes for stochastic non-convex optimization. In International Conference on Machine Learning. PMLR, 7174--7183."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853589"},{"key":"e_1_3_2_1_21_1","volume":"201","author":"Zinkevich Martin","unstructured":"Martin Zinkevich, Markus Weimer, Lihong Li, and Alex J Smola. 2010. Parallelized stochastic gradient descent. In Advances in neural information processing systems. 2595--2603.","journal-title":"Alex J Smola."}],"event":{"name":"CF '22: 19th ACM International Conference on Computing Frontiers","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"],"location":"Turin Italy","acronym":"CF '22"},"container-title":["Proceedings of the 19th ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530246","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3528416.3530246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:42Z","timestamp":1750186962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530246"}},"subtitle":["adaptively accelerating distributed deep learning in heterogeneous environments"],"short-title":[],"issued":{"date-parts":[[2022,5,17]]},"references-count":21,"alternative-id":["10.1145\/3528416.3530246","10.1145\/3528416"],"URL":"https:\/\/doi.org\/10.1145\/3528416.3530246","relation":{},"subject":[],"published":{"date-parts":[[2022,5,17]]},"assertion":[{"value":"2022-05-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}