{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T01:59:10Z","timestamp":1775959150748,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,11,12]],"date-time":"2017-11-12T00:00:00Z","timestamp":1510444800000},"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":[[2017,11,12]]},"DOI":"10.1145\/3146347.3146351","type":"proceedings-article","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T12:31:37Z","timestamp":1509453097000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Accelerating deep neural network learning for speech recognition on a cluster of GPUs"],"prefix":"10.1145","author":[{"given":"Guojing","family":"Cong","sequence":"first","affiliation":[{"name":"IBM Research, Yorktown Heights, New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumyadip","family":"Gosh","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, North Avenue NW, Atlanta, Georgia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,11,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"L Bottou F. E. Curtis and J Nocedal. Optimization methods for large-scale machine learning. 2017.  L Bottou F. E. Curtis and J Nocedal. Optimization methods for large-scale machine learning. 2017.","DOI":"10.1137\/16M1080173"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0572-5"},{"key":"e_1_3_2_1_3_1","unstructured":"NVIDIA cuDNN -- GPU accelerated deep learning https:\/\/developer.nvidia.com\/cudnn.  NVIDIA cuDNN -- GPU accelerated deep learning https:\/\/developer.nvidia.com\/cudnn."},{"key":"e_1_3_2_1_4_1","first-page":"1223","volume-title":"Advances in Neural Information Processing Systems 25","author":"Dean J.","year":"2012"},{"key":"e_1_3_2_1_5_1","unstructured":"O. Dekel R. Gilad-Bachrach O. Shamir and L. Xiao. Optimal distributed online prediction using mini-batches. Journal of Machine Learning Research 13(Jan):165--202 2012.  O. Dekel R. Gilad-Bachrach O. Shamir and L. Xiao. Optimal distributed online prediction using mini-batches. Journal of Machine Learning Research 13(Jan):165--202 2012."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2014.7020221"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_10_1","unstructured":"D.P. Kingma and J. Ba. Adam: A method for stochastic optimization. CoRR abs\/1412.6980 2015.  D.P. Kingma and J. Ba. Adam: A method for stochastic optimization. CoRR abs\/1412.6980 2015."},{"key":"e_1_3_2_1_11_1","unstructured":"2000 HUB5 English evaluation speech. https:\/\/catalog.ldc.upenn.edu\/LDC2002S09.  2000 HUB5 English evaluation speech. https:\/\/catalog.ldc.upenn.edu\/LDC2002S09."},{"key":"e_1_3_2_1_12_1","unstructured":"2000 HUB5 English evaluation transcripts. https:\/\/catalog.ldc.upenn.edu\/LDC2002T43.  2000 HUB5 English evaluation transcripts. https:\/\/catalog.ldc.upenn.edu\/LDC2002T43."},{"key":"e_1_3_2_1_13_1","unstructured":"Switchboard-1 release 2. https:\/\/catalog.ldc.upenn.edu\/LDC97S62.  Switchboard-1 release 2. https:\/\/catalog.ldc.upenn.edu\/LDC97S62."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"e_1_3_2_1_15_1","first-page":"2737","volume-title":"Advances in Neural Information Processing Systems","author":"Lian X.","year":"2015"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404777"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.382443"},{"key":"e_1_3_2_1_18_1","unstructured":"mpiT--MPI for Torch https:\/\/github.com\/sixin-zh\/mpiT.  mpiT--MPI for Torch https:\/\/github.com\/sixin-zh\/mpiT."},{"key":"e_1_3_2_1_19_1","volume-title":"SIAM Journal of Optimization","author":"Pasupathy R","year":"2017"},{"key":"e_1_3_2_1_20_1","unstructured":"J. Picone. Switchboard resegmentation project. https:\/\/www.isip.piconepress.com\/projects\/switchboard\/.  J. Picone. Switchboard resegmentation project. https:\/\/www.isip.piconepress.com\/projects\/switchboard\/."},{"key":"e_1_3_2_1_21_1","first-page":"693","volume-title":"Advances in Neural Information Processing Systems","author":"Recht B.","year":"2011"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"e_1_3_2_1_23_1","unstructured":"Torch -- A scientific computing framework for Luajit http:\/\/torch.ch.  Torch -- A scientific computing framework for Luajit http:\/\/torch.ch."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Zhang S.","year":"2015"},{"key":"e_1_3_2_1_26_1","unstructured":"F. Zhou and G. Cong. On the convergence properties of a k-step averaging stochastic gradient descent algorithm for nonconvex optimization. arXiv: 1708.01012 [cs.LG] August 2017. https:\/\/arxiv.org\/abs\/1708.01012.  F. Zhou and G. Cong. On the convergence properties of a k-step averaging stochastic gradient descent algorithm for nonconvex optimization. arXiv: 1708.01012 [cs.LG] August 2017. https:\/\/arxiv.org\/abs\/1708.01012."}],"event":{"name":"SC '17: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '17","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the Machine Learning on HPC Environments"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3146347.3146351","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3146347.3146351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:13:33Z","timestamp":1750212813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3146347.3146351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,12]]},"references-count":26,"alternative-id":["10.1145\/3146347.3146351","10.1145\/3146347"],"URL":"https:\/\/doi.org\/10.1145\/3146347.3146351","relation":{},"subject":[],"published":{"date-parts":[[2017,11,12]]},"assertion":[{"value":"2017-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}