{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:43:38Z","timestamp":1774219418991,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"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":["CCF-1750656"],"award-info":[{"award-number":["CCF-1750656"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1704662"],"award-info":[{"award-number":["CNS-1704662"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1739748"],"award-info":[{"award-number":["CNS-1739748"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1717984"],"award-info":[{"award-number":["CNS-1717984"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1733701"],"award-info":[{"award-number":["CCF-1733701"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1717754"],"award-info":[{"award-number":["CCF-1717754"]}],"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":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304076","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"925-938","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":116,"title":["ADMM-NN"],"prefix":"10.1145","author":[{"given":"Ao","family":"Ren","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}]},{"given":"Tianyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Syracuse University, Syracuse, NY, USA"}]},{"given":"Shaokai","family":"Ye","sequence":"additional","affiliation":[{"name":"Syracuse University, Syracuse, NY, USA"}]},{"given":"Jiayu","family":"Li","sequence":"additional","affiliation":[{"name":"Syracuse University, Syracuse, NY, USA"}]},{"given":"Wenyao","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Buffalo, SUNY, Buffalo, NY, USA"}]},{"given":"Xuehai","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"http:\/\/www.techradar.com\/news\/computing-components\/processors\/google-s-tensor-processing-unit-explained-this-is-what-the-future-of-computing-looks-like-1326915."},{"key":"e_1_3_2_1_2_1","unstructured":"https:\/\/www.sdxcentral.com\/articles\/news\/intels-deep-learning-chips-will-arrive-2017\/2016\/11\/."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295077"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870355"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541967"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2749425"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969588"},{"key":"e_1_3_2_1_10_1","unstructured":"Dai X. Yin H. and Jha N. K.Nest: a neural network synthesis toolbased on a grow-and-prune paradigm. arXiv preprint arXiv:1711.02017(2017)."},{"key":"e_1_3_2_1_11_1","first-page":"248","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2009)","author":"Deng J.","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2009), pp. 248--255."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968968"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870349"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124552"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295239"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_1_18_1","first-page":"18","volume-title":"Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture(2017)","author":"Guo K.","unstructured":"Guo, K., Han, S., Yao, S., Wang, Y., Xie, Y., and Yang, H.Software-hardware code sign for efficient neural network acceleration. In Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture(2017), IEEE Computer Society, pp. 18--25."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157251"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Learning Representations (ICLR)(2016)","author":"Han S.","unstructured":"Han, S., Mao, H., and Dally, W. J. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In International Conference on Learning Representations (ICLR)(2016)."},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations (ICLR)(2017)","author":"Han S.","unstructured":"Han, S., Pool, J., Narang, S., Mao, H., Gong, E., Tang, S., Elsen,E., Vajda, P., Paluri, M., Tran, J., et al. Dsd: Dense-sparse-dense training for deep neural networks. In International Conference on Learning Representations (ICLR)(2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969366"},{"key":"e_1_3_2_1_25_1","first-page":"770","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition(2016)","author":"He K.","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J.Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition(2016), pp. 770--778."},{"key":"e_1_3_2_1_26_1","first-page":"1398","volume-title":"Computer Vision (ICCV), 2017 IEEE International Conference on(2017)","author":"He Y.","unstructured":"He, Y., Zhang, X., and Sun, J.Channel pruning for accelerating very deep neural networks. In Computer Vision (ICCV), 2017 IEEE International Conference on(2017), IEEE, pp. 1398--1406."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157557"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195661"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Learning Representations (ICLR)(2016)","author":"Kingma D.","unstructured":"Kingma, D., and Ba, L. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR)(2016)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_2_1_32_1","unstructured":"LeCun Y. et al. Lenet-5 convolutional neural networks. URL: http:\/\/yann.lecun.com\/exdb\/lenet(2015) 20."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Leng C. Li H. Zhu S. and Jin R. Extremely low bit neural network: Squeeze the last bit out with admm. arXiv preprint arXiv:1707.09870(2017).","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045690"},{"key":"e_1_3_2_1_35_1","first-page":"14","volume-title":"High Performance Computer Architecture (HPCA), 2016 IEEE International Symposium on(2016)","author":"Mahajan D.","unstructured":"Mahajan, D., Park, J., Amaro, E., Sharma, H., Yazdanbakhsh, A.,Kim, J. K., and Esmaeilzadeh, H.Tabla: A unified template-based framework for accelerating statistical machine learning. In High Performance Computer Architecture (HPCA), 2016 IEEE International Symposium on(2016), IEEE, pp. 14--26."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Mao H. Han S. Pool J. Li W. Liu X. Wang Y. and Dally W. J. Exploring the regularity of sparse structure in convolutional neural networks. arXiv preprint arXiv:1705.08922(2017).","DOI":"10.1109\/CVPRW.2017.241"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870353"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3042828"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_40_1","first-page":"7197","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2017)","author":"Park E.","unstructured":"Park, E., Ahn, J., and Yoo, S. Weighted-entropy-based quantization for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2017), pp. 7197--7205."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_42_1","first-page":"525","volume-title":"European Conference on Computer Vision(2016)","author":"Rastegari M.","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., and Farhadi, A. Xnor-net: Imagenet classification using binary convolutional neural networks. In European Conference on Computer Vision(2016), Springer, pp. 525--542."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418008"},{"key":"e_1_3_2_1_46_1","unstructured":"Simonyan K. and Zisserman A.Very deep convolutional networksfor large-scale image recognition. arXiv preprint arXiv: 1409.1556(2014)."},{"key":"e_1_3_2_1_47_1","volume-title":"International Conference on Learning Representations (ICLR)(2015)","author":"Simonyan K.","unstructured":"Simonyan, K., and Zisserman, A. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR)(2015)."},{"key":"e_1_3_2_1_48_1","first-page":"92","volume-title":"High Performance Computer Architecture(HPCA), 2018 IEEE International Symposium on(2018)","author":"Song M.","unstructured":"Song, M., Zhong, K., Zhang, J., Hu, Y., Liu, D., Zhang, W., Wang, J., and Li, T.In-situ ai: Towards autonomous and incremental deep learning for iot systems. In High Performance Computer Architecture(HPCA), 2018 IEEE International Symposium on(2018), IEEE, pp. 92--103."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3042863"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870351"},{"key":"e_1_3_2_1_55_1","first-page":"4820","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2016)","author":"Wu J.","unstructured":"Wu, J., Leng, C., Wang, Y., Hu, Q., and Cheng, J. Quantized con-volutional neural networks for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2016), pp. 4820--4828."},{"key":"e_1_3_2_1_56_1","first-page":"6071","volume-title":"Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition(2017)","author":"Yang T.-J.","unstructured":"Yang, T.-J., Chen, Y.-H., and Sze, V. Designing energy-efficient convolutional neural networks using energy-aware pruning. In Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition(2017), pp. 6071--6079."},{"key":"e_1_3_2_1_57_1","unstructured":"Ye S. Zhang T. Zhang K. Li J. Xie J. Liang Y. Liu S. Lin X. and Wang Y.A unified framework of dnn weight pruning and weight clustering\/quantization using admm. arXiv preprint arXiv:1811.01907(2018)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"e_1_3_2_1_59_1","first-page":"7370","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2017)","author":"Yu X.","unstructured":"Yu, X., Liu, T., Wang, X., and Tao, D. On compressing deep modelsby low rank and sparse decomposition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2017), pp. 7370--7379."},{"key":"e_1_3_2_1_60_1","first-page":"33","volume-title":"2018 IEEE Symposium on VLSI Circuits(2018)","author":"Yuan Z.","unstructured":"Yuan, Z., Yue, J., Yang, H., Wang, Z., Li, J., Yang, Y., Guo, Q., Li, X., Chang, M.-F., Yang, H., et al. Sticker: A 0.41--62.1 tops\/w 8bit neural network processor with multi-sparsity compatible convolution arrays and online tuning acceleration for fully connected layers. In 2018 IEEE Symposium on VLSI Circuits(2018), IEEE, pp. 33--34."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967011"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"e_1_3_2_1_63_1","unstructured":"Zhang D. Wang H. Figueiredo M. and Balzano L. Learningto share: Simultaneous parameter tying and sparsification in deeplearning."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Zhang T. Ye S. Zhang K. Tang J. Wen W. Fardad M. and Wang Y.A systematic dnn weight pruning framework using alternating direction method of multipliers. arXiv preprint arXiv:1804.03294(2018).","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"e_1_3_2_1_66_1","volume-title":"International Conference on Learning Representations (ICLR)(2017)","author":"Zhou A.","unstructured":"Zhou, A., Yao, A., Guo, Y., Xu, L., and Chen, Y. Incremental network quantization: Towards lossless cnns with low-precision weights. In International Conference on Learning Representations (ICLR)(2017)."},{"key":"e_1_3_2_1_67_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhu C.","year":"2017","unstructured":"Zhu, C., Han, S., Mao, H., and Dally, W. J. Trained ternary quantization. In International Conference on Learning Representations (ICLR) (2017)."}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","location":"Providence RI USA","acronym":"ASPLOS '19","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304076","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304076","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:15Z","timestamp":1750204395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304076"}},"subtitle":["An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Methods of Multipliers"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":67,"alternative-id":["10.1145\/3297858.3304076","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304076","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}