{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:43:46Z","timestamp":1775123026110,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,10]],"date-time":"2018-06-10T00:00:00Z","timestamp":1528588800000},"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":[[2018,6,10]]},"DOI":"10.1145\/3210240.3210337","type":"proceedings-article","created":{"date-parts":[[2018,7,6]],"date-time":"2018-07-06T12:36:06Z","timestamp":1530880566000},"page":"389-400","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":177,"title":["On-Demand Deep Model Compression for Mobile Devices"],"prefix":"10.1145","author":[{"given":"Sicong","family":"Liu","sequence":"first","affiliation":[{"name":"Xidian University"}]},{"given":"Yingyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Rice University"}]},{"given":"Zimu","family":"Zhou","sequence":"additional","affiliation":[{"name":"ETH Zurich"}]},{"given":"Kaiming","family":"Nan","sequence":"additional","affiliation":[{"name":"Xidian University"}]},{"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University"}]},{"given":"Junzhao","family":"Du","sequence":"additional","affiliation":[{"name":"Xidian University"}]}],"member":"320","published-online":{"date-parts":[[2018,6,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of ICML","author":"Achiam Joshua","year":"2017","unstructured":"Joshua Achiam , David Held , Aviv Tamar , and Pieter Abbeel . 2017 . Constrained Policy Optimization . Proceedings of ICML (2017). Joshua Achiam, David Held, Aviv Tamar, and Pieter Abbeel. 2017. Constrained Policy Optimization. Proceedings of ICML (2017)."},{"key":"e_1_3_2_2_2_1","volume-title":"Deep compositional question answering with neural module networks. arXiv preprint arXiv:1511.02799 2","author":"Andreas Jacob","year":"2015","unstructured":"Jacob Andreas , Marcus Rohrbach , Trevor Darrell , and Dan Klein . 2015. Deep compositional question answering with neural module networks. arXiv preprint arXiv:1511.02799 2 ( 2015 ). Jacob Andreas, Marcus Rohrbach, Trevor Darrell, and Dan Klein. 2015. Deep compositional question answering with neural module networks. arXiv preprint arXiv:1511.02799 2 (2015)."},{"key":"e_1_3_2_2_3_1","volume-title":"Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940","author":"Bello Irwan","year":"2017","unstructured":"Irwan Bello , Hieu Pham , Quoc V Le , Mohammad Norouzi , and Samy Bengio . 2017. Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940 ( 2017 ). Irwan Bello, Hieu Pham, Quoc V Le, Mohammad Norouzi, and Samy Bengio. 2017. Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940 (2017)."},{"key":"e_1_3_2_2_4_1","volume-title":"Random search for hyper-parameter optimization. Journal of Machine Learning Research","author":"Bergstra James","year":"2012","unstructured":"James Bergstra and Yoshua Bengio . 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research ( 2012 ). James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research (2012)."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of NIPS.","author":"Bergstra James S","year":"2011","unstructured":"James S Bergstra , R\u00e9mi Bardenet , Yoshua Bengio , and Bal\u00e1zs K\u00e9gl . 2011 . Algorithms for hyper-parameter optimization . In Proceedings of NIPS. James S Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. In Proceedings of NIPS."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2994551.2994564"},{"key":"e_1_3_2_2_7_1","volume-title":"The power of sparsity in convolutional neural networks. arXiv preprint arXiv:1702.06257","author":"Changpinyo Soravit","year":"2017","unstructured":"Soravit Changpinyo , Mark Sandler , and Andrey Zhmoginov . 2017. The power of sparsity in convolutional neural networks. arXiv preprint arXiv:1702.06257 ( 2017 ). Soravit Changpinyo, Mark Sandler, and Andrey Zhmoginov. 2017. The power of sparsity in convolutional neural networks. arXiv preprint arXiv:1702.06257 (2017)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of IJCAI.","author":"Domhan Tobias","year":"2015","unstructured":"Tobias Domhan , Jost Tobias Springenberg , and Frank Hutter . 2015 . Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves .. In Proceedings of IJCAI. Tobias Domhan, Jost Tobias Springenberg, and Frank Hutter. 2015. Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves.. In Proceedings of IJCAI."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131693"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2973750.2973777"},{"key":"e_1_3_2_2_14_1","volume-title":"https:\/\/goo.gl\/j7HAZJ","year":"2017","unstructured":"Google. 2017. TensorFlow. ( 2017 ). https:\/\/goo.gl\/j7HAZJ . Google. 2017. TensorFlow. (2017). https:\/\/goo.gl\/j7HAZJ."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of ICLR.","author":"Han Song","year":"2016","unstructured":"Song Han , Huizi Mao , and William J Dally . 2016 . Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding . In Proceedings of ICLR. Song Han, Huizi Mao, and William J Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In Proceedings of ICLR."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_2_2_18_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3089331"},{"key":"e_1_3_2_2_20_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and &lt","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola , Song Han , Matthew W Moskewicz , Khalid Ashraf , William J Dally , and Kurt Keutzer . 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and &lt ; 0.5 MB model size. arXiv preprint arXiv:1602.07360 ( 2016 ). Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"e_1_3_2_2_21_1","unstructured":"Kazufumi Ito and Karl Kunisch. 2008. Lagrange multiplier approach to variational problems and applications. SIAM.   Kazufumi Ito and Karl Kunisch. 2008. Lagrange multiplier approach to variational problems and applications. SIAM."},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of ICLR.","author":"Kingma Diederik","year":"2015","unstructured":"Diederik Kingma and Jimmy Ba . 2015 . Adam:A method for stochastic optimization . In Proceedings of ICLR. Diederik Kingma and Jimmy Ba. 2015. Adam:A method for stochastic optimization. In Proceedings of ICLR."},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings of NIPS.","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012 . ImageNet Classification with Deep Convolutional Neural Networks . In Proceedings of NIPS. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of NIPS."},{"key":"e_1_3_2_2_24_1","unstructured":"Alex Krizhevsky Nair Vinod and Hinton Geoffrey. 2014. The CIFAR-10 dataset. https:\/\/goo.gl\/hXmru5. (2014).  Alex Krizhevsky Nair Vinod and Hinton Geoffrey. 2014. The CIFAR-10 dataset. https:\/\/goo.gl\/hXmru5. (2014)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2959355.2959378"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699343.2699349"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2804262"},{"key":"e_1_3_2_2_28_1","unstructured":"Yann LeCun. 1998. The MNIST database of handwritten digits. https:\/\/goo.gl\/t6gTEy. (1998).  Yann LeCun. 1998. The MNIST database of handwritten digits. https:\/\/goo.gl\/t6gTEy. (1998)."},{"key":"e_1_3_2_2_29_1","volume-title":"https:\/\/goo.gl\/APBzd5","author":"LeCun Yan","year":"2017","unstructured":"Yan LeCun . 2017. LeNet. ( 2017 ). https:\/\/goo.gl\/APBzd5 . Yan LeCun. 2017. LeNet. (2017). https:\/\/goo.gl\/APBzd5."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057233"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of ICLR.","author":"Lin Min","year":"2014","unstructured":"Min Lin , Qiang Chen , and Shuicheng Yan . 2014 . Network in network . In Proceedings of ICLR. Min Lin, Qiang Chen, and Shuicheng Yan. 2014. Network in network. In Proceedings of ICLR."},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of CVPR.","author":"Liu Baoyuan","year":"2015","unstructured":"Baoyuan Liu , Min Wang , Hassan Foroosh , Marshall Tappen , and Marianna Pensky . 2015 . Sparse convolutional neural networks . In Proceedings of CVPR. Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, and Marianna Pensky. 2015. Sparse convolutional neural networks. In Proceedings of CVPR."},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of AAAI.","author":"Liu Lanlan","year":"2018","unstructured":"Lanlan Liu and Jia Deng . 2018 . Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution . In Proceedings of AAAI. Lanlan Liu and Jia Deng. 2018. Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution. In Proceedings of AAAI."},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of INFOCOM.","author":"Liu Yang","year":"2018","unstructured":"Yang Liu and Zhenjiang Li . 2018 . iType: Using eye gaze to enhance typing privacy . In Proceedings of INFOCOM. Yang Liu and Zhenjiang Li. 2018. iType: Using eye gaze to enhance typing privacy. In Proceedings of INFOCOM."},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of NIPS Workshops.","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Alex Graves , Ioannis Antonoglou , Daan Wierstra , and Martin Riedmiller . 2013 . Playing atari with deep reinforcement learning . In Proceedings of NIPS Workshops. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. In Proceedings of NIPS Workshops."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3090082"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of ICLR.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman . 2015 . Very deep convolutional networks for large-scale image recognition . In Proceedings of ICLR. Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of ICLR."},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of NIPS.","author":"Snoek Jasper","year":"2012","unstructured":"Jasper Snoek , Hugo Larochelle , and Ryan P Adams . 2012 . Practical bayesian optimization of machine learning algorithms . In Proceedings of NIPS. Jasper Snoek, Hugo Larochelle, and Ryan P Adams. 2012. Practical bayesian optimization of machine learning algorithms. In Proceedings of NIPS."},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of ICML. 2171--2180","author":"Snoek Jasper","year":"2015","unstructured":"Jasper Snoek , Oren Rippel , Kevin Swersky , Ryan Kiros , Nadathur Satish , Narayanan Sundaram , Mostofa Patwary , Mr Prabhat , and Ryan Adams . 2015 . Scalable bayesian optimization using deep neural networks . In Proceedings of ICML. 2171--2180 . Jasper Snoek, Oren Rippel, Kevin Swersky, Ryan Kiros, Nadathur Satish, Narayanan Sundaram, Mostofa Patwary, Mr Prabhat, and Ryan Adams. 2015. Scalable bayesian optimization using deep neural networks. In Proceedings of ICML. 2171--2180."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of NIPS.","author":"Springenberg Jost Tobias","year":"2016","unstructured":"Jost Tobias Springenberg , Aaron Klein , Stefan Falkner , and Frank Hutter . 2016 . Bayesian optimization with robust Bayesian neural networks . In Proceedings of NIPS. Jost Tobias Springenberg, Aaron Klein, Stefan Falkner, and Frank Hutter. 2016. Bayesian optimization with robust Bayesian neural networks. In Proceedings of NIPS."},{"key":"e_1_3_2_2_41_1","volume-title":"Efficient processing of deep neural networks: A tutorial and survey. arXiv preprint arXiv:1703.09039","author":"Sze Vivienne","year":"2017","unstructured":"Vivienne Sze , Yu-Hsin Chen , Tien-Ju Yang , and Joel Emer . 2017. Efficient processing of deep neural networks: A tutorial and survey. arXiv preprint arXiv:1703.09039 ( 2017 ). Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, and Joel Emer. 2017. Efficient processing of deep neural networks: A tutorial and survey. arXiv preprint arXiv:1703.09039 (2017)."},{"key":"e_1_3_2_2_42_1","unstructured":"UCI. 2017. Dataset for Human Activity Recognition. https:\/\/goo.gl\/m5bRo1. (2017).  UCI. 2017. Dataset for Human Activity Recognition. https:\/\/goo.gl\/m5bRo1. (2017)."},{"key":"e_1_3_2_2_43_1","volume-title":"Proceedings of AAAI.","author":"Hasselt Hado Van","year":"2016","unstructured":"Hado Van Hasselt , Arthur Guez , and David Silver . 2016 . Deep Reinforcement Learning with Double Q-Learning .. In Proceedings of AAAI. Hado Van Hasselt, Arthur Guez, and David Silver. 2016. Deep Reinforcement Learning with Double Q-Learning.. In Proceedings of AAAI."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056828"},{"key":"e_1_3_2_2_46_1","volume-title":"Marc Lanctot, and Nando De Freitas.","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang , Tom Schaul , Matteo Hessel , Hado Van Hasselt , Marc Lanctot, and Nando De Freitas. 2016 . Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581 (2016). Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Van Hasselt, Marc Lanctot, and Nando De Freitas. 2016. Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581 (2016)."},{"key":"e_1_3_2_2_47_1","volume-title":"Enabling Cooperative Inference of Deep Learning on Wearables and Smartphones. arXiv preprint arXiv:1712.03073","author":"Xu Mengwei","year":"2017","unstructured":"Mengwei Xu , Feng Qian , and Saumay Pushp . 2017. Enabling Cooperative Inference of Deep Learning on Wearables and Smartphones. arXiv preprint arXiv:1712.03073 ( 2017 ). Mengwei Xu, Feng Qian, and Saumay Pushp. 2017. Enabling Cooperative Inference of Deep Learning on Wearables and Smartphones. arXiv preprint arXiv:1712.03073 (2017)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2752367"},{"key":"e_1_3_2_2_50_1","volume-title":"Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578","author":"Zoph Barret","year":"2016","unstructured":"Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 ( 2016 ). Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)."},{"key":"e_1_3_2_2_51_1","volume-title":"Learning Transferable Architectures for Scalable Image Recognition. arXiv preprint arXiv:1707.07012","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph , Vijay Vasudevan , Jonathon Shlens , and Quoc V Le. 2017. Learning Transferable Architectures for Scalable Image Recognition. arXiv preprint arXiv:1707.07012 ( 2017 ). Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V Le. 2017. Learning Transferable Architectures for Scalable Image Recognition. arXiv preprint arXiv:1707.07012 (2017)."}],"event":{"name":"MobiSys '18: The 16th Annual International Conference on Mobile Systems, Applications, and Services","location":"Munich Germany","acronym":"MobiSys '18","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3210240.3210337","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3210240.3210337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:48Z","timestamp":1750210788000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3210240.3210337"}},"subtitle":["A Usage-Driven Model Selection Framework"],"short-title":[],"issued":{"date-parts":[[2018,6,10]]},"references-count":51,"alternative-id":["10.1145\/3210240.3210337","10.1145\/3210240"],"URL":"https:\/\/doi.org\/10.1145\/3210240.3210337","relation":{},"subject":[],"published":{"date-parts":[[2018,6,10]]},"assertion":[{"value":"2018-06-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}