{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:54:39Z","timestamp":1743083679998,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030056766"},{"type":"electronic","value":"9783030056773"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-05677-3_10","type":"book-chapter","created":{"date-parts":[[2018,12,29]],"date-time":"2018-12-29T20:33:30Z","timestamp":1546115610000},"page":"114-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Data Fine-Pruning: A Simple Way to Accelerate Neural Network Training"],"prefix":"10.1007","author":[{"given":"Junyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ligang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenyuan","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,30]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-7908-2604-3_16","volume-title":"Proceedings of COMPSTAT 2010","author":"L Bottou","year":"2010","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Lechevallier, Y., Saporta, G. (eds.) COMPSTAT 2010, pp. 177\u2013186. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-7908-2604-3_16"},{"key":"10_CR2","unstructured":"Chilimbi, T.M., Suzue, Y., Apacible, J., Kalyanaraman, K.: Project adam: building an efficient and scalable deep learning training system. In: OSDI, vol. 14, pp. 571\u2013582 (2014)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Cire\u015fan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. arXiv preprint arXiv:1202.2745 (2012)","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Cui, H., Zhang, H., Ganger, G.R., Gibbons, P.B., Xing, E.P.: GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server. In: Proceedings of the Eleventh European Conference on Computer Systems, p. 4. ACM (2016)","DOI":"10.1145\/2901318.2901323"},{"issue":"1","key":"10_CR5","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10_CR6","unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: Advances in Neural Information Processing Systems, pp. 1223\u20131231 (2012)"},{"issue":"Jul","key":"10_CR7","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"10_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"7553","key":"10_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)","journal-title":"Nature"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Lei, Y., Scheffer, N., Ferrer, L., McLaren, M.: A novel scheme for speaker recognition using a phonetically-aware deep neural network. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1695\u20131699. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853887"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Scaling distributed machine learning with the parameter server. In: OSDI, vol. 14, pp. 583\u2013598 (2014)","DOI":"10.1145\/2640087.2644155"},{"issue":"1","key":"10_CR14","first-page":"285","volume":"16","author":"J Liu","year":"2015","unstructured":"Liu, J., Wright, S.J., R\u00e9, C., Bittorf, V., Sridhar, S.: An asynchronous parallel stochastic coordinate descent algorithm. J. Mach. Learn. Res. 16(1), 285\u2013322 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR15","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcementlearning. In: International Conference on Machine Learning, pp. 1928\u20131937(2016)"},{"key":"10_CR16","unstructured":"Nesterov, Y.: A method for unconstrained convex minimization problem with the rate of convergence $$\\text{o}(1\/{\\rm k}^2)$$. In: Doklady AN USSR, vol. 269, pp. 543\u2013547 (1983)"},{"issue":"1","key":"10_CR17","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145\u2013151 (1999)","journal-title":"Neural Netw."},{"key":"10_CR18","unstructured":"Recht, B., Re, C., Wright, S., Niu, F.: HOGWILD: a lock-free approach to parallelizing stochastic gradient descent. In: Advances in Neural Information Processing Systems, pp. 693\u2013701 (2011)"},{"issue":"10","key":"10_CR19","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson, F., Reynolds, D., Dehak, N.: Deep neural network approaches to speaker and language recognition. IEEE Sig. Process. Lett. 22(10), 1671\u20131675 (2015)","journal-title":"IEEE Sig. Process. Lett."},{"key":"10_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"1","key":"10_CR21","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701\u20131708 (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"10_CR24","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"key":"10_CR25","unstructured":"Zheng, S., et al.: Asynchronous stochastic gradient descent with delay compensation. In: International Conference on Machine Learning (2017)"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05677-3_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T01:35:42Z","timestamp":1672277742000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-05677-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030056766","9783030056773"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05677-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"30 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Muroran","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pacman.cs.tsinghua.edu.cn\/npc2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}