{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T16:29:26Z","timestamp":1757780966471},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2017,6,15]],"date-time":"2017-06-15T00:00:00Z","timestamp":1497484800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Peer-to-Peer Netw. Appl."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s12083-017-0574-4","type":"journal-article","created":{"date-parts":[[2017,6,15]],"date-time":"2017-06-15T00:39:58Z","timestamp":1497487198000},"page":"1012-1021","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Training deep neural network on multiple GPUs with a model averaging method"],"prefix":"10.1007","volume":"11","author":[{"given":"Qiongjie","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,6,15]]},"reference":[{"key":"574_CR1","doi-asserted-by":"crossref","unstructured":"Chen K, Huo Q (2016) Scalable training of deep learning machines by incremental block training with intra-block parallel optimization and blockwise model-update filtering. In: Proceedings of the 2016 IEEE international conference on acoustics, speech and signal processing, pp 5880\u20135884","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"574_CR2","unstructured":"Chen T, Li M, Li Y, Lin M, Wang N, Wang M, Xiao T, Xu B, Zhang C, Zhang Z (2015) Mxnet: a flexible and efficient machine learning library for heterogeneous distributed systems. In: Proceedings of the workshop on machine learning systems with the 29th annual conference on neural information processing systems (NIPS), pp 80\u201386"},{"key":"574_CR3","unstructured":"Coates A, Huval B, Wang T, Wu D, Catanzaro B, Andrew N (2013) Deep learning with cots hpc systems. In: Proceedings of the 30th international conference on machine learning (ICML), pp 1337\u20131345"},{"key":"574_CR4","doi-asserted-by":"crossref","unstructured":"Cui H, Zhang H, Ganger G R, Gibbons P B, Xing E P (2016) Geeps: scalable deep learning on distributed gpus with a gpu-specialized parameter server. In: Proceedings of the eleventh European conference on computer systems, (EuroSys), pp 1\u201316","DOI":"10.1145\/2901318.2901323"},{"key":"574_CR5","unstructured":"Dean J, Corrado G, Monga R, Chen K, Devin M, Le Q V, Mao M Z, Ranzato M, Senior A W, Tucker P A, Yang K, Ng A Y (2012) Large scale distributed deep networks. In: Proceedings of the 26th annual conference on neural information processing systems (NIPS), pp 1223\u20131231"},{"key":"574_CR6","doi-asserted-by":"crossref","unstructured":"Dong L, Wei F, Zhou M, Xu K (2014) Adaptive multi-compositionality for recursive neural models with applications to sentiment analysis. In: Proceedings of the 28th AAAI conference on artificial intelligence (AAAI), pp 1537\u20131543","DOI":"10.1609\/aaai.v28i1.8930"},{"issue":"7","key":"574_CR7","first-page":"1","volume":"59","author":"W Gao","year":"2016","unstructured":"Gao W, Zhou Z H (2016) Dropout rademacher complexity of deep neural networks. Sci Chin Inf Sci 59 (7):1\u201312","journal-title":"Sci Chin Inf Sci"},{"key":"574_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013781","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"574_CR9","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton G, Deng L, Yu D, Dahl G E, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82\u201397","journal-title":"IEEE Signal Process Mag"},{"issue":"7","key":"574_CR10","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton G E, Osindero S, Teh Y W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527\u20131554","journal-title":"Neural Comput"},{"key":"574_CR11","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"574_CR12","unstructured":"Krizhevsky A (2014) One weird trick for parallelizing convolutional neural networks. Eprint Arxiv"},{"key":"574_CR13","unstructured":"Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the 26th annual conference on neural information processing systems (NIPS), pp 1097\u20131105"},{"key":"574_CR14","doi-asserted-by":"crossref","unstructured":"Le Q V (2013) Building high-level features using large scale unsupervised learning. In: Proceedings of the 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 8595\u20138598","DOI":"10.1109\/ICASSP.2013.6639343"},{"issue":"4","key":"574_CR15","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B E, Denker J S, Henderson D, Howard R E, Hubbard W E, Jackel L D (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551","journal-title":"Neural Comput"},{"key":"574_CR16","doi-asserted-by":"crossref","unstructured":"Li M, Andersen DG, Park JW, Smola AJ, Ahmed A, Josifovski V, Long J, Shekita E J, Su B Y (2014) Scaling distributed machine learning with the parameter server. In: Proceedings of the 11th USENIX symposium on operating systems design and implementation (OSDI), pp 583\u2013598","DOI":"10.1145\/2640087.2644155"},{"key":"574_CR17","doi-asserted-by":"crossref","unstructured":"Li X, Zhang G, Huang HH, Wang Z, Zheng W (2016) Performance analysis of gpu-based convolutional neural networks. In: Proceedings of the 45th international conference on parallel processing, pp 67\u201376","DOI":"10.1109\/ICPP.2016.15"},{"key":"574_CR18","unstructured":"Mann G, Mcdonald RT, Mohri M, Silberman N, Dan W, Mann G, Mcdonald RT, Mohri M, Silberman N, Dan W (2009) Efficient large-scale distributed training of conditional maximum entropy models. In: Proceedings of the 23rd annual conference on neural information processing systems, pp 1231\u20131239"},{"key":"574_CR19","unstructured":"Martens J (2010) Deep learning via hessian-free optimization. In: Proceedings of the 30th international conference on machine learning (ICML), pp 1337\u20131345"},{"key":"574_CR20","unstructured":"Mcmahan HB, Moore E, Ramage D, Arcas BAY (2016) Federated learning of deep networks using model averaging. Eprint Arxiv"},{"key":"574_CR21","unstructured":"Ngiam J, Coates A, Lahiri A, Prochnow B, Le Q V, Ng AY (2011) On optimization methods for deep learning. In: Proceedings of the 28th international conference on machine learning (ICML), pp 265\u2013272"},{"key":"574_CR22","doi-asserted-by":"crossref","unstructured":"Raina R, Madhavan A, Ng AY (2009) Large-scale deep unsupervised learning using graphics processors. In: Proceedings of the 26th international conference on machine learning (ICML), pp 873\u2013880","DOI":"10.1145\/1553374.1553486"},{"key":"574_CR23","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proceedings of the 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"9","key":"574_CR24","doi-asserted-by":"crossref","first-page":"1961","DOI":"10.1007\/s11432-011-4342-4","volume":"55","author":"XJ Yang","year":"2012","unstructured":"Yang XJ, Tao T, Wang GB (2012) Mptostream:an openmp compiler for cpu-gpu heterogeneous parallel systems. Sci Chin Inf Sci 55(9):1961\u20131971","journal-title":"Sci Chin Inf Sci"},{"issue":"1","key":"574_CR25","first-page":"3321","volume":"14","author":"Y Zhang","year":"2013","unstructured":"Zhang Y, Duchi JC, Wainwright MJ (2013) Communication-efficient algorithms for statistical optimization. J Mach Learn Res 14(1):3321\u20133363","journal-title":"J Mach Learn Res"},{"issue":"7","key":"574_CR26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-015-5351-5","volume":"58","author":"Y Zhi","year":"2015","unstructured":"Zhi Y, Yang Y (2015) Discrete control of longitudinal dynamics for hypersonic flight vehicle using neural networks. Sci Chin Inf Sci 58(7):1\u201310","journal-title":"Sci Chin Inf Sci"},{"key":"574_CR27","unstructured":"Zinkevich M, Weimer M, Smola AJ, Li L (2010) Parallelized stochastic gradient descent, pp 2595\u20132603"},{"issue":"13","key":"574_CR28","first-page":"1772","volume":"7","author":"Y Zou","year":"2014","unstructured":"Zou Y, Jin X, Li Y, Guo Z, Wang E, Xiao B (2014) Mariana: tencent deep learning platform and its applications. PVLDB 7(13):1772\u20131777","journal-title":"PVLDB"}],"container-title":["Peer-to-Peer Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12083-017-0574-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-017-0574-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-017-0574-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T18:04:46Z","timestamp":1659117886000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12083-017-0574-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,15]]},"references-count":28,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["574"],"URL":"https:\/\/doi.org\/10.1007\/s12083-017-0574-4","relation":{},"ISSN":["1936-6442","1936-6450"],"issn-type":[{"value":"1936-6442","type":"print"},{"value":"1936-6450","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6,15]]}}}