{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T04:52:54Z","timestamp":1772254374031,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T00:00:00Z","timestamp":1561161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1900713, 1822989, 1822459, 1527535, 1423090, 1320100"],"award-info":[{"award-number":["1900713, 1822989, 1822459, 1527535, 1423090, 1320100"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322263","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"292-303","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["Eager pruning"],"prefix":"10.1145","author":[{"given":"Jiaqi","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Florida"}]},{"given":"Xiangru","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Florida"}]},{"given":"Mingcong","family":"Song","sequence":"additional","affiliation":[{"name":"University of Florida"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Florida"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_2_1","unstructured":"Andrej Karpathy. What I learned from competing against a ConvNet on ImageNet: http:\/\/karpathy.github.io\/2014\/09\/02\/what-i-learned-from-competing-against-a-convnet-on-imagenet\/."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.655647"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/5680264"},{"key":"e_1_3_2_1_5_1","volume-title":"Cancer","author":"Floyd Carey E.","year":"1994","unstructured":"Carey E. Floyd, Joseph Y. Lo, A. Joon Yun, Daniel C. Sullivan, and Phyllis J. Kornguth. Prediction of breast cancer malignancy using an artificial neural network, Cancer, 1994."},{"key":"e_1_3_2_1_6_1","unstructured":"Big Data vs. Fast Data: https:\/\/www.voltdb.com\/why-voltdb\/big-data\/."},{"key":"e_1_3_2_1_7_1","unstructured":"Internet Live Stats: http:\/\/www.internetlivestats.com."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_9_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In arXiv:1409.1556","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. In arXiv:1409.1556, 2015."},{"key":"e_1_3_2_1_10_1","volume-title":"Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes. In arXiv:1711.04325","author":"Akiba Takuya","year":"2017","unstructured":"Takuya Akiba, Shuji Suzuki, and Keisuke Fukuda. Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes. In arXiv:1711.04325, 2017."},{"key":"e_1_3_2_1_11_1","volume-title":"ImageNet Training in Minutes. In arXiv:1709.05011","author":"You Yang","year":"2018","unstructured":"Yang You, Zhao Zhang, Cho-Jui Hsieh, James Demmel, and Kurt Keutzer. ImageNet Training in Minutes. In arXiv:1709.05011, 2018."},{"key":"e_1_3_2_1_12_1","unstructured":"Sriram Subramanian. Modern AI Stack & AI as a Service Consumption Models: https:\/\/medium.com\/clouddon\/modern-ai-stack-ai-service-consumption-models-f9957dce7b25."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969366"},{"key":"e_1_3_2_1_14_1","volume-title":"Dally","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J. Dally. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. In arXiv:1510.00149, 2015."},{"key":"e_1_3_2_1_15_1","volume-title":"ISCA","author":"Yu Jiecao","year":"2017","unstructured":"Jiecao Yu, Andrew Lukefahr, David Palframan, Ganesh Dasika, Reetuparna Das, and Scott Mahlke. Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism. In ISCA, 2017."},{"key":"e_1_3_2_1_16_1","unstructured":"Backpropagation In Convolutional Neural Networks: http:\/\/www.jefkine.com\/general\/2016\/09\/05\/backpropagation-in-convolutional-neural-networks\/."},{"key":"e_1_3_2_1_17_1","unstructured":"BackPropagation Through Time: https:\/\/pdfs.semanticscholar.org\/c77f\/7264096cc9555cd0533c0dc28e909f9977f2.pdf."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_1_19_1","volume-title":"An overview of gradient descent optimization algorithms. In arXiv:1609.04747","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder. An overview of gradient descent optimization algorithms. In arXiv:1609.04747, 2017."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815993"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_23_1","volume-title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network. In ISCA","author":"Han Song","year":"2016","unstructured":"Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, and William J. Dally. EIE: Efficient Inference Engine on Compressed Deep Neural Network. In ISCA, 2016."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195662"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/4492.4495"},{"key":"e_1_3_2_1_30_1","author":"LeCun Yann","year":"1989","unstructured":"Yann LeCun, L.D. Jackel, B. Boser, J.S. Denker, H.P. Graf, I. Guyon, D. Henderson, R.E. Howard, and W. Hubbard. Handwritten digit recognition: applications of neural network chips and automatic learning, Commun. Mag., 1989.","journal-title":"Mag."},{"key":"e_1_3_2_1_31_1","volume-title":"ICLR","author":"Lin Min","year":"2014","unstructured":"Min Lin, Qiang Chen, and Shuicheng Yan. Network in network. In ICLR, 2014."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969197"},{"key":"e_1_3_2_1_34_1","volume-title":"INTERSPEECH","author":"Sak Ha\u015fim","year":"2014","unstructured":"Ha\u015fim Sak, Andrew Senior, and Fran\u00e7oise Beaufays. Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling. In INTERSPEECH, 2014."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_36_1","volume-title":"The Kaldi Speech Recognition Toolkit","author":"Povey Daniel","year":"2011","unstructured":"Daniel Povey, Arnab Ghoshal, Gilles Boulianne, and Lukas Burget. The Kaldi Speech Recognition Toolkit, 2011."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"e_1_3_2_1_38_1","unstructured":"WattsUp: https:\/\/www.wattsupmeters.com\/."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tust.2018.07.006"},{"key":"e_1_3_2_1_40_1","volume-title":"Symmetry (Basel).","author":"Liu Bin","year":"2018","unstructured":"Bin Liu, Yun Zhang, DongJian He, and Yuxiang Li. Identification of Apple Leaf Diseases Based on Deep Convolutional Neural Networks, Symmetry (Basel)., 2018."},{"key":"e_1_3_2_1_41_1","unstructured":"Jon Jordan. Opinion: Why your game needs to load within 30 seconds: https:\/\/www.pocketgamer.biz\/monetizer\/59041\/opinion-why-your-game-needs-to-load-within-30-seconds\/."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294853"},{"key":"e_1_3_2_1_47_1","volume-title":"MICRO","author":"Ding Caiwen","year":"2017","unstructured":"Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yipeng Zhang, Jian Tang, Qinru Qiu, Xue Lin, and Bo Yuan. CirCNN: accelerating and compressing deep neural networks using block-circulant weight matrices. In MICRO, 2017."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_2_1_49_1","volume-title":"Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks. In HPCA","author":"Rhu Minsoo","year":"2018","unstructured":"Minsoo Rhu, Mike O'Connor, Niladrish Chatterjee, Jeff Pool, and Stephen W. Keckler. Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks. In HPCA, 2018."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00021"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00023"},{"key":"e_1_3_2_1_52_1","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky. Learning Multiple Layers of Features from Tiny Images, 2009."},{"key":"e_1_3_2_1_53_1","volume-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1","author":"Garofolo John S.","year":"1993","unstructured":"John S. Garofolo, Lori F. Lamel, William M. Fisher, Jonathan G. Fiscus, David S. Pallett, Nancy L. Dahlgren, and Victor Zue. TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1. In Linguistic Data Consortium, 1993."}],"event":{"name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona","acronym":"ISCA '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"]},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322263","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322263","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:06Z","timestamp":1750204446000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322263"}},"subtitle":["algorithm and architecture support for fast training of deep neural networks"],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":53,"alternative-id":["10.1145\/3307650.3322263","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322263","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}