乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:13:41Z","timestamp":1726762421994},"reference-count":213,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Things"],"published-print":{"date-parts":[[2021,8,31]]},"abstract":"The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with increasing numbers of smart devices and improved hardware, there is interest in performing model training on the device. Given this surge in interest, a comprehensive survey of the field from a device-agnostic perspective sets the stage for both understanding the state of the art and for identifying open challenges and future avenues of research. However, on-device learning is an expansive field with connections to a large number of related topics in AI and machine learning (including online learning, model adaptation, one\/few-shot learning, etc.). Hence, covering such a large number of topics in a single survey is impractical. This survey finds a middle ground by reformulating the problem of on-device learning as resource constrained learning where the resources are compute and memory. This reformulation allows tools, techniques, and algorithms from a wide variety of research areas to be compared equitably. In addition to summarizing the state of the art, the survey also identifies a number of challenges and next steps for both the algorithmic and theoretical aspects of on-device learning.<\/jats:p>","DOI":"10.1145\/3450494","type":"journal-article","created":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T13:52:56Z","timestamp":1625752376000},"page":"1-49","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":69,"title":["A Survey of On-Device Machine Learning"],"prefix":"10.1145","volume":"2","author":[{"given":"Sauptik","family":"Dhar","sequence":"first","affiliation":[{"name":"America Research Center, LG Electronics"}]},{"given":"Junyao","family":"Guo","sequence":"additional","affiliation":[{"name":"America Research Center, LG Electronics"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6007-5256","authenticated-orcid":false,"given":"Jiayi (Jason)","family":"Liu","sequence":"additional","affiliation":[{"name":"America Research Center, LG Electronics"}]},{"given":"Samarth","family":"Tripathi","sequence":"additional","affiliation":[{"name":"America Research Center, LG Electronics"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3427-0418","authenticated-orcid":false,"given":"Unmesh","family":"Kurup","sequence":"additional","affiliation":[{"name":"America Research Center, LG Electronics"}]},{"given":"Mohak","family":"Shah","sequence":"additional","affiliation":[{"name":"America Research Center, LG Electronics"}]}],"member":"320","published-online":{"date-parts":[[2021,7,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.09.068"},{"key":"e_1_2_1_3_1","volume-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems. 1709\u20131720.","author":"Alistarh Dan","year":"2017","unstructured":"Dan Alistarh , Demjan Grubic , Jerry Li , Ryota Tomioka , and Milan Vojnovic . 2017 . QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems. 1709\u20131720. Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, and Milan Vojnovic. 2017. QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems. 1709\u20131720."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS\u201917)","author":"Allen-Zhu Zeyuan","year":"2017","unstructured":"Zeyuan Allen-Zhu and Yuanzhi Li . 2017 . First efficient convergence for streaming k-pca: A global, gap-free, and near-optimal rate . In Proceedings of the 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS\u201917) . IEEE, 487\u2013492. Zeyuan Allen-Zhu and Yuanzhi Li. 2017. First efficient convergence for streaming k-pca: A global, gap-free, and near-optimal rate. In Proceedings of the 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS\u201917). IEEE, 487\u2013492."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1545"},{"key":"e_1_2_1_6_1","volume-title":"Bartlett and Shahar Mendelson","author":"Peter","year":"2002","unstructured":"Peter L. Bartlett and Shahar Mendelson . 2002 . Rademacher and Gaussian complexities: Risk bounds and structural results. J. Mach. Learn. Res . 3 (Nov. 2002), 463\u2013482. Peter L. Bartlett and Shahar Mendelson. 2002. Rademacher and Gaussian complexities: Risk bounds and structural results. J. Mach. Learn. Res. 3 (Nov. 2002), 463\u2013482."},{"key":"e_1_2_1_7_1","volume-title":"Shayan Oveis Gharan, and Xin Yang","author":"Beame Paul","year":"2017","unstructured":"Paul Beame , Shayan Oveis Gharan, and Xin Yang . 2017 . Time-space tradeoffs for learning from small test spaces: Learning low degree polynomial functions. arXiv:1708.02640. Retrieved from https:\/\/arxiv.orb\/abs\/1708.02640. Paul Beame, Shayan Oveis Gharan, and Xin Yang. 2017. Time-space tradeoffs for learning from small test spaces: Learning low degree polynomial functions. arXiv:1708.02640. Retrieved from https:\/\/arxiv.orb\/abs\/1708.02640."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1998.1569"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the Annual Conference on Learning Theory (COLT\u201990)","author":"Ben-David Shai","year":"1990","unstructured":"Shai Ben-David , Alon Itai , and Eyal Kushilevitz . 1990 . Learning by distances . In Proceedings of the Annual Conference on Learning Theory (COLT\u201990) . 232\u2013245. Shai Ben-David, Alon Itai, and Eyal Kushilevitz. 1990. Learning by distances. In Proceedings of the Annual Conference on Learning Theory (COLT\u201990). 232\u2013245."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877890"},{"key":"e_1_2_1_11_1","unstructured":"Tolga Bolukbasi Joseph Wang Ofer Dekel and Venkatesh Saligrama. 2017. Adaptive neural networks for efficient inference. arXiv:1702.07811. Retrieved from https:\/\/arxiv.org\/abs\/1702.07811. Tolga Bolukbasi Joseph Wang Ofer Dekel and Venkatesh Saligrama. 2017. Adaptive neural networks for efficient inference. arXiv:1702.07811. Retrieved from https:\/\/arxiv.org\/abs\/1702.07811."},{"key":"e_1_2_1_12_1","unstructured":"Brian Bullins Elad Hazan and Tomer Koren. 2016. The limits of learning with missing data. In Advances in Neural Information Processing Systems. 3495\u20133503. Brian Bullins Elad Hazan and Tomer Koren. 2016. The limits of learning with missing data. In Advances in Neural Information Processing Systems. 3495\u20133503."},{"key":"e_1_2_1_13_1","volume-title":"Neuralpower: Predict and deploy energy-efficient convolutional neural networks. arXiv:1710.05420.","author":"Cai Ermao","year":"2017","unstructured":"Ermao Cai , Da-Cheng Juan , Dimitrios Stamoulis , and Diana Marculescu . 2017 . Neuralpower: Predict and deploy energy-efficient convolutional neural networks. arXiv:1710.05420. Retrieved from https:\/\/arxiv.org\/abs\/1710.05420. Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, and Diana Marculescu. 2017. Neuralpower: Predict and deploy energy-efficient convolutional neural networks. arXiv:1710.05420. Retrieved from https:\/\/arxiv.org\/abs\/1710.05420."},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS\u201920)","author":"Cai Han","year":"2020","unstructured":"Han Cai , Chuang Gan , Ligeng Zhu , and Song Han . 2020 . TinyTL: Reduce memory, not parameters for efficient on-device learning . In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS\u201920) . Han Cai, Chuang Gan, Ligeng Zhu, and Song Han. 2020. TinyTL: Reduce memory, not parameters for efficient on-device learning. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS\u201920)."},{"key":"e_1_2_1_15_1","volume-title":"Proxylessnas: Direct neural architecture search on target task and hardware. arXiv:1812.00332. Retrieved from arxiv.org\/abs\/1812.00332.","author":"Cai Han","year":"2018","unstructured":"Han Cai , Ligeng Zhu , and Song Han . 2018 . Proxylessnas: Direct neural architecture search on target task and hardware. arXiv:1812.00332. Retrieved from arxiv.org\/abs\/1812.00332. Han Cai, Ligeng Zhu, and Song Han. 2018. Proxylessnas: Direct neural architecture search on target task and hardware. arXiv:1812.00332. Retrieved from arxiv.org\/abs\/1812.00332."},{"key":"e_1_2_1_16_1","unstructured":"L\u00e9opold Cambier Anahita Bhiwandiwalla Ting Gong Mehran Nekuii Oguz H. Elibol and Hanlin Tang. 2020. Shifted and squeezed 8-bit floating point format for low-precision training of deep neural networks. arXiv:2001.05674. Retrieved from arxiv.org\/abs\/2001.05674. L\u00e9opold Cambier Anahita Bhiwandiwalla Ting Gong Mehran Nekuii Oguz H. Elibol and Hanlin Tang. 2020. Shifted and squeezed 8-bit floating point format for low-precision training of deep neural networks. arXiv:2001.05674. Retrieved from arxiv.org\/abs\/2001.05674."},{"key":"e_1_2_1_17_1","unstructured":"Alfredo Canziani Adam Paszke and Eugenio Culurciello. 2016. An analysis of deep neural network models for practical applications. arXiv:1605.07678. Retrieved from https:\/\/arxiv.org\/abs\/1605.07678. Alfredo Canziani Adam Paszke and Eugenio Culurciello. 2016. An analysis of deep neural network models for practical applications. arXiv:1605.07678. Retrieved from https:\/\/arxiv.org\/abs\/1605.07678."},{"key":"e_1_2_1_18_1","volume-title":"Efficient learning with partially observed attributes. J. Mach. Learn. Res. 12 (Oct","author":"Cesa-Bianchi Nicolo","year":"2011","unstructured":"Nicolo Cesa-Bianchi , Shai Shalev-Shwartz , and Ohad Shamir . 2011. Efficient learning with partially observed attributes. J. Mach. Learn. Res. 12 (Oct . 2011 ), 2857\u20132878. Nicolo Cesa-Bianchi, Shai Shalev-Shwartz, and Ohad Shamir. 2011. Efficient learning with partially observed attributes. J. Mach. Learn. Res. 12 (Oct. 2011), 2857\u20132878."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2015974"},{"key":"e_1_2_1_20_1","unstructured":"Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv:1604.06174. Retrieved from https:\/\/arxiv.org\/abs\/1604.06174. Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv:1604.06174. Retrieved from https:\/\/arxiv.org\/abs\/1604.06174."},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of the International Conference on Machine Learning. 2285\u20132294","author":"Chen Wenlin","year":"2015","unstructured":"Wenlin Chen , James Wilson , Stephen Tyree , Kilian Weinberger , and Yixin Chen . 2015 . Compressing neural networks with the hashing trick . In Proceedings of the International Conference on Machine Learning. 2285\u20132294 . Wenlin Chen, James Wilson, Stephen Tyree, Kilian Weinberger, and Yixin Chen. 2015. Compressing neural networks with the hashing trick. In Proceedings of the International Conference on Machine Learning. 2285\u20132294."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598304"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"An-Chieh Cheng Jin-Dong Dong Chi-Hung Hsu Shu-Huan Chang Min Sun Shih-Chieh Chang Jia-Yu Pan Yu-Ting Chen Wei Wei and Da-Cheng Juan. 2018. Searching toward pareto-optimal device-aware neural architectures. arXiv:1808.09830. Retrieved from https:\/\/arxiv.org\/abs\/1808.09830. An-Chieh Cheng Jin-Dong Dong Chi-Hung Hsu Shu-Huan Chang Min Sun Shih-Chieh Chang Jia-Yu Pan Yu-Ting Chen Wei Wei and Da-Cheng Juan. 2018. Searching toward pareto-optimal device-aware neural architectures. arXiv:1808.09830. Retrieved from https:\/\/arxiv.org\/abs\/1808.09830.","DOI":"10.1145\/3240765.3243494"},{"key":"e_1_2_1_25_1","volume-title":"Mulier","author":"Cherkassky Vladimir","year":"2007","unstructured":"Vladimir Cherkassky and Filip M . Mulier . 2007 . Learning from Data : Concepts, Theory, and Methods. John Wiley & Sons . Vladimir Cherkassky and Filip M. Mulier. 2007. Learning from Data: Concepts, Theory, and Methods. John Wiley & Sons."},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the 1993 International Conference on Neural Networks (IJCNN\u201993)","volume":"2","author":"Choi H.","year":"1947","unstructured":"H. Choi , W. P. Burleson , and D. S. Phatak . 1993. Fixed-point roundoff error analysis of large feedforward neural networks . In Proceedings of the 1993 International Conference on Neural Networks (IJCNN\u201993) , Vol. 2 . IEEE, 1947 \u20131950. H. Choi, W. P. Burleson, and D. S. Phatak. 1993. Fixed-point roundoff error analysis of large feedforward neural networks. In Proceedings of the 1993 International Conference on Neural Networks (IJCNN\u201993), Vol. 2. IEEE, 1947\u20131950."},{"key":"e_1_2_1_27_1","volume-title":"Ng","author":"Chu Cheng-Tao","year":"2007","unstructured":"Cheng-Tao Chu , Sang K. Kim , Yi-An Lin , YuanYuan Yu , Gary Bradski , Kunle Olukotun , and Andrew Y . Ng . 2007 . Map-reduce for machine learning on multicore. In Advances in Neural Information Processing Systems . 281\u2013288. Cheng-Tao Chu, Sang K. Kim, Yi-An Lin, YuanYuan Yu, Gary Bradski, Kunle Olukotun, and Andrew Y. Ng. 2007. Map-reduce for machine learning on multicore. In Advances in Neural Information Processing Systems. 281\u2013288."},{"key":"e_1_2_1_28_1","first-page":"102","article-title":"DAWNBench: An end-to-end deep learning benchmark and competition","volume":"100","author":"Coleman Cody","year":"2017","unstructured":"Cody Coleman , Deepak Narayanan , Daniel Kang , Tian Zhao , Jian Zhang , Luigi Nardi , Peter Bailis , Kunle Olukotun , Chris R\u00e9 , and Matei Zaharia . 2017 . DAWNBench: An end-to-end deep learning benchmark and competition . Training 100 , 101 (2017), 102 . Cody Coleman, Deepak Narayanan, Daniel Kang, Tian Zhao, Jian Zhang, Luigi Nardi, Peter Bailis, Kunle Olukotun, Chris R\u00e9, and Matei Zaharia. 2017. DAWNBench: An end-to-end deep learning benchmark and competition. Training 100, 101 (2017), 102.","journal-title":"Training"},{"key":"e_1_2_1_29_1","volume-title":"Binaryconnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems. 3123\u20133131.","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux , Yoshua Bengio , and Jean-Pierre David . 2015 . Binaryconnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems. 3123\u20133131. Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. Binaryconnect: Training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems. 3123\u20133131."},{"key":"e_1_2_1_30_1","unstructured":"Matthieu Courbariaux Itay Hubara Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv:1602.02830. Retrieved from https:\/\/arxiv.org\/abs\/1602.02830. Matthieu Courbariaux Itay Hubara Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv:1602.02830. Retrieved from https:\/\/arxiv.org\/abs\/1602.02830."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5327-x"},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 11398\u201311407","author":"Dai Xiaoliang","year":"2019","unstructured":"Xiaoliang Dai , Peizhao Zhang , Bichen Wu , Hongxu Yin , Fei Sun , Yanghan Wang , Marat Dukhan , Yunqing Hu , Yiming Wu , Yangqing Jia , et\u00a0al. 2019 . Chamnet: Towards efficient network design through platform-aware model adaptation . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 11398\u201311407 . Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, et\u00a0al. 2019. Chamnet: Towards efficient network design through platform-aware model adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 11398\u201311407."},{"key":"e_1_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Amit Daniely Nati Linial and Shai Shalev-Shwartz. 2013. From average case complexity to improper learning complexity. arXiv:1311.2272. Retrieved from https:\/\/arxiv.org\/abs\/1311.2272. Amit Daniely Nati Linial and Shai Shalev-Shwartz. 2013. From average case complexity to improper learning complexity. arXiv:1311.2272. Retrieved from https:\/\/arxiv.org\/abs\/1311.2272.","DOI":"10.1145\/2591796.2591820"},{"key":"e_1_2_1_34_1","unstructured":"Amit Daniely Nati Linial and Shai Shalev-Shwartz. 2013. More data speeds up training time in learning halfspaces over sparse vectors. In Advances in Neural Information Processing Systems. 145\u2013153. Amit Daniely Nati Linial and Shai Shalev-Shwartz. 2013. More data speeds up training time in learning halfspaces over sparse vectors. In Advances in Neural Information Processing Systems. 145\u2013153."},{"key":"e_1_2_1_35_1","volume-title":"Retrieved","author":"Dasgupta Saumitro","year":"2020","unstructured":"Saumitro Dasgupta and David Gschwend . Netscope CNN Analyzer . Retrieved December 22, 2020 from https:\/\/dgschwend.github.io\/netscope\/quickstart.html. Saumitro Dasgupta and David Gschwend. Netscope CNN Analyzer. Retrieved December 22, 2020 from https:\/\/dgschwend.github.io\/netscope\/quickstart.html."},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 44th Annual International Symposium on Computer Architecture. 561\u2013574","author":"Sa Christopher De","year":"2017","unstructured":"Christopher De Sa , Matthew Feldman , Christopher R\u00e9 , and Kunle Olukotun . 2017 . Understanding and optimizing asynchronous low-precision stochastic gradient descent . In Proceedings of the 44th Annual International Symposium on Computer Architecture. 561\u2013574 . Christopher De Sa, Matthew Feldman, Christopher R\u00e9, and Kunle Olukotun. 2017. Understanding and optimizing asynchronous low-precision stochastic gradient descent. In Proceedings of the 44th Annual International Symposium on Computer Architecture. 561\u2013574."},{"key":"e_1_2_1_37_1","unstructured":"Christopher De Sa Megan Leszczynski Jian Zhang Alana Marzoev Christopher R. Aberger Kunle Olukotun and Christopher R\u00e9. 2018. High-accuracy low-precision training. arXiv:1803.03383. Retrieved from https:\/\/arxiv.org\/abs\/1803.03383. Christopher De Sa Megan Leszczynski Jian Zhang Alana Marzoev Christopher R. Aberger Kunle Olukotun and Christopher R\u00e9. 2018. High-accuracy low-precision training. arXiv:1803.03383. Retrieved from https:\/\/arxiv.org\/abs\/1803.03383."},{"key":"e_1_2_1_38_1","unstructured":"Christopher M De Sa Ce Zhang Kunle Olukotun and Christopher R\u00e9. 2015. Taming the wild: A unified analysis of hogwild-style algorithms. In Advances in Neural Information Processing Systems. 2674\u20132682. Christopher M De Sa Ce Zhang Kunle Olukotun and Christopher R\u00e9. 2015. Taming the wild: A unified analysis of hogwild-style algorithms. In Advances in Neural Information Processing Systems. 2674\u20132682."},{"key":"e_1_2_1_39_1","volume-title":"et\u00a0al","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean , Greg Corrado , Rajat Monga , Kai Chen , Matthieu Devin , Mark Mao , Andrew Senior , Paul Tucker , Ke Yang , Quoc V. Le , et\u00a0al . 2012 . Large scale distributed deep networks. In Advances in Neural Information Processing Systems . 1223\u20131231. Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Andrew Senior, Paul Tucker, Ke Yang, Quoc V. Le, et\u00a0al. 2012. Large scale distributed deep networks. In Advances in Neural Information Processing Systems. 1223\u20131231."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539797325648"},{"key":"e_1_2_1_41_1","volume-title":"Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems. 25\u201330","author":"Dey Swarnava","year":"2019","unstructured":"Swarnava Dey , Arijit Mukherjee , and Arpan Pal . 2019 . Embedded deep inference in practice: Case for model partitioning . In Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems. 25\u201330 . Swarnava Dey, Arijit Mukherjee, and Arpan Pal. 2019. Embedded deep inference in practice: Case for model partitioning. In Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems. 25\u201330."},{"key":"e_1_2_1_42_1","unstructured":"Sauptik Dhar Vladimir Cherkassky and Mohak Shah. 2019. Multiclass learning from contradictions. In Advances in Neural Information Processing Systems. 8400\u20138410. Sauptik Dhar Vladimir Cherkassky and Mohak Shah. 2019. Multiclass learning from contradictions. In Advances in Neural Information Processing Systems. 8400\u20138410."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2262037"},{"key":"e_1_2_1_44_1","unstructured":"Angela Fan Pierre Stock Benjamin Graham Edouard Grave Remi Gribonval Herve Jegou and Armand Joulin. 2020. Training with quantization noise for extreme model compression. arxiv:cs.LG\/2004.07320. Retrieved from https:\/\/arxiv.org\/abs\/2004.07320. Angela Fan Pierre Stock Benjamin Graham Edouard Grave Remi Gribonval Herve Jegou and Armand Joulin. 2020. Training with quantization noise for extreme model compression. arxiv:cs.LG\/2004.07320. Retrieved from https:\/\/arxiv.org\/abs\/2004.07320."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"e_1_2_1_46_1","volume-title":"Efficiency and Computational Limitations of Learning Algorithms","author":"\u00a0al Vitaly Feldman","unstructured":"Vitaly Feldman et \u00a0al . 2007. Efficiency and Computational Limitations of Learning Algorithms . Vol. 68 . Vitaly Feldman et\u00a0al. 2007. Efficiency and Computational Limitations of Learning Algorithms. Vol. 68."},{"key":"e_1_2_1_47_1","volume-title":"Proceedings of the 45th Annual ACM Symposium on Theory of Computing. ACM, 655\u2013664","author":"Feldman Vitaly","year":"2013","unstructured":"Vitaly Feldman , Elena Grigorescu , Lev Reyzin , Santosh Vempala , and Ying Xiao . 2013 . Statistical algorithms and a lower bound for detecting planted cliques . In Proceedings of the 45th Annual ACM Symposium on Theory of Computing. ACM, 655\u2013664 . Vitaly Feldman, Elena Grigorescu, Lev Reyzin, Santosh Vempala, and Ying Xiao. 2013. Statistical algorithms and a lower bound for detecting planted cliques. In Proceedings of the 45th Annual ACM Symposium on Theory of Computing. ACM, 655\u2013664."},{"key":"e_1_2_1_48_1","volume-title":"Proceedings of the 28th Annual ACM-SIAM Symposium on Discrete Algorithms. SIAM, 1265\u20131277","author":"Feldman Vitaly","year":"2017","unstructured":"Vitaly Feldman , Crist\u00f3bal Guzm\u00e1n , and Santosh Vempala . 2017 . Statistical query algorithms for mean vector estimation and stochastic convex optimization . In Proceedings of the 28th Annual ACM-SIAM Symposium on Discrete Algorithms. SIAM, 1265\u20131277 . Vitaly Feldman, Crist\u00f3bal Guzm\u00e1n, and Santosh Vempala. 2017. Statistical query algorithms for mean vector estimation and stochastic convex optimization. In Proceedings of the 28th Annual ACM-SIAM Symposium on Discrete Algorithms. SIAM, 1265\u20131277."},{"key":"e_1_2_1_49_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 2749\u20132757","author":"Feng Jiashi","year":"2015","unstructured":"Jiashi Feng and Trevor Darrell . 2015 . Learning the structure of deep convolutional networks . In Proceedings of the IEEE International Conference on Computer Vision. 2749\u20132757 . Jiashi Feng and Trevor Darrell. 2015. Learning the structure of deep convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision. 2749\u20132757."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2697065"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.12.010"},{"key":"e_1_2_1_52_1","volume-title":"Raj Kumar Maity, and Arya Mazumdar","author":"Gandikota Venkata","year":"2019","unstructured":"Venkata Gandikota , Raj Kumar Maity, and Arya Mazumdar . 2019 . vqSGD: Vector quantized stochastic gradient descent. arXiv:1911.07971. Retrieved from https:\/\/arxiv.orb\/abs\/1911.07971. Venkata Gandikota, Raj Kumar Maity, and Arya Mazumdar. 2019. vqSGD: Vector quantized stochastic gradient descent. arXiv:1911.07971. Retrieved from https:\/\/arxiv.orb\/abs\/1911.07971."},{"key":"e_1_2_1_53_1","volume-title":"et\u00a0al","author":"Gao Wanling","year":"2018","unstructured":"Wanling Gao , Jianfeng Zhan , Lei Wang , Chunjie Luo , Daoyi Zheng , Rui Ren , Chen Zheng , Gang Lu , Jingwei Li , Zheng Cao , et\u00a0al . 2018 . BigDataBench: A dwarf-based big data and AI benchmark suite. arXiv:1802.08254. Retrieved from https:\/\/arxiv.orb\/abs\/1802.08254. Wanling Gao, Jianfeng Zhan, Lei Wang, Chunjie Luo, Daoyi Zheng, Rui Ren, Chen Zheng, Gang Lu, Jingwei Li, Zheng Cao, et\u00a0al. 2018. BigDataBench: A dwarf-based big data and AI benchmark suite. arXiv:1802.08254. Retrieved from https:\/\/arxiv.orb\/abs\/1802.08254."},{"key":"e_1_2_1_54_1","volume-title":"Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing. ACM, 990\u20131002","author":"Garg Sumegha","year":"2018","unstructured":"Sumegha Garg , Ran Raz , and Avishay Tal . 2018 . Extractor-based time-space lower bounds for learning . In Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing. ACM, 990\u20131002 . Sumegha Garg, Ran Raz, and Avishay Tal. 2018. Extractor-based time-space lower bounds for learning. In Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing. ACM, 990\u20131002."},{"key":"e_1_2_1_55_1","volume-title":"Recent advances in open set recognition: A survey","author":"Geng Chuanxing","year":"2020","unstructured":"Chuanxing Geng , Sheng-jun Huang, and Songcan Chen . 2020. Recent advances in open set recognition: A survey . IEEE Trans. Pattern Anal. Mach. Intell . ( 2020 ). Chuanxing Geng, Sheng-jun Huang, and Songcan Chen. 2020. Recent advances in open set recognition: A survey. IEEE Trans. Pattern Anal. Mach. Intell. (2020)."},{"key":"e_1_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Amir Gholami Kiseok Kwon Bichen Wu Zizheng Tai Xiangyu Yue Peter Jin Sicheng Zhao and Kurt Keutzer. 2018. SqueezeNext: Hardware-aware neural network design. arXiv:1803.10615. Retrieved from https:\/\/arxiv.org\/abs\/1803.10615. Amir Gholami Kiseok Kwon Bichen Wu Zizheng Tai Xiangyu Yue Peter Jin Sicheng Zhao and Kurt Keutzer. 2018. SqueezeNext: Hardware-aware neural network design. arXiv:1803.10615. Retrieved from https:\/\/arxiv.org\/abs\/1803.10615.","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"e_1_2_1_57_1","volume-title":"Proceedings of the 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD\u201918)","author":"Gianniti Eugenio","year":"2018","unstructured":"Eugenio Gianniti , Li Zhang , and Danilo Ardagna . 2018 . Performance prediction of gpu-based deep learning applications . In Proceedings of the 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD\u201918) . IEEE, 167\u2013170. Eugenio Gianniti, Li Zhang, and Danilo Ardagna. 2018. Performance prediction of gpu-based deep learning applications. In Proceedings of the 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD\u201918). IEEE, 167\u2013170."},{"key":"e_1_2_1_58_1","volume-title":"Proceedings of the International Conference on Machine Learning. 325\u2013333","author":"Golovin Daniel","year":"2013","unstructured":"Daniel Golovin , D. Sculley , Brendan McMahan , and Michael Young . 2013 . Large-scale learning with less ram via randomization . In Proceedings of the International Conference on Machine Learning. 325\u2013333 . Daniel Golovin, D. Sculley, Brendan McMahan, and Michael Young. 2013. Large-scale learning with less ram via randomization. In Proceedings of the International Conference on Machine Learning. 325\u2013333."},{"key":"e_1_2_1_59_1","unstructured":"Yunchao Gong Liu Liu Ming Yang and Lubomir Bourdev. 2014. Compressing deep convolutional networks using vector quantization. arXiv:1412.6115. Retrieved from https:\/\/arxiv.org\/abs\/1412.6115. Yunchao Gong Liu Liu Ming Yang and Lubomir Bourdev. 2014. Compressing deep convolutional networks using vector quantization. arXiv:1412.6115. Retrieved from https:\/\/arxiv.org\/abs\/1412.6115."},{"key":"e_1_2_1_60_1","unstructured":"Ian J. Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv:1412.6572. Retrieved from https:\/\/arxiv.org\/abs\/1412.6572. Ian J. Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv:1412.6572. Retrieved from https:\/\/arxiv.org\/abs\/1412.6572."},{"key":"e_1_2_1_61_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201917)","author":"Greff Klaus","year":"2017","unstructured":"Klaus Greff , Rupesh K. Srivastava , and J\u00fcrgen Schmidhuber . 2017 . Highway and residual networks learn unrolled iterative estimation . In Proceedings of the International Conference on Learning Representations (ICLR\u201917) . Klaus Greff, Rupesh K. Srivastava, and J\u00fcrgen Schmidhuber. 2017. Highway and residual networks learn unrolled iterative estimation. In Proceedings of the International Conference on Learning Representations (ICLR\u201917)."},{"key":"e_1_2_1_62_1","volume-title":"Speedboost: Anytime prediction with uniform near-optimality. In Artificial Intelligence and Statistics. 458\u2013466.","author":"Grubb Alex","year":"2012","unstructured":"Alex Grubb and Drew Bagnell . 2012 . Speedboost: Anytime prediction with uniform near-optimality. In Artificial Intelligence and Statistics. 458\u2013466. Alex Grubb and Drew Bagnell. 2012. Speedboost: Anytime prediction with uniform near-optimality. In Artificial Intelligence and Statistics. 458\u2013466."},{"key":"e_1_2_1_63_1","unstructured":"Audrunas Gruslys R\u00e9mi Munos Ivo Danihelka Marc Lanctot and Alex Graves. 2016. Memory-efficient backpropagation through time. In Advances in Neural Information Processing Systems. 4125\u20134133. Audrunas Gruslys R\u00e9mi Munos Ivo Danihelka Marc Lanctot and Alex Graves. 2016. Memory-efficient backpropagation through time. In Advances in Neural Information Processing Systems. 4125\u20134133."},{"key":"e_1_2_1_64_1","unstructured":"Renjie Gu Shuo Yang and Fan Wu. 2019. Distributed machine learning on mobile devices: A survey. arXiv:1909.08329. Retrieved from https:\/\/arxiv.org\/abs\/1909.08329. Renjie Gu Shuo Yang and Fan Wu. 2019. Distributed machine learning on mobile devices: A survey. arXiv:1909.08329. Retrieved from https:\/\/arxiv.org\/abs\/1909.08329."},{"key":"e_1_2_1_65_1","unstructured":"Yunhui Guo. 2018. A survey on methods and theories of quantized neural networks. arXiv:1808.04752. Retrieved from https:\/\/arxiv.org\/abs\/1808.04752. Yunhui Guo. 2018. A survey on methods and theories of quantized neural networks. arXiv:1808.04752. Retrieved from https:\/\/arxiv.org\/abs\/1808.04752."},{"key":"e_1_2_1_66_1","volume-title":"Proceedings of the International Conference on Machine Learning. 1737\u20131746","author":"Gupta Suyog","year":"2015","unstructured":"Suyog Gupta , Ankur Agrawal , Kailash Gopalakrishnan , and Pritish Narayanan . 2015 . Deep learning with limited numerical precision . In Proceedings of the International Conference on Machine Learning. 1737\u20131746 . Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan. 2015. Deep learning with limited numerical precision. In Proceedings of the International Conference on Machine Learning. 1737\u20131746."},{"key":"e_1_2_1_68_1","volume-title":"Dally","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J . Dally . 2015 . Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv:1510.00149. Retrieved from https:\/\/arxiv.orb\/abs\/1510.00149. Song Han, Huizi Mao, and William J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv:1510.00149. Retrieved from https:\/\/arxiv.orb\/abs\/1510.00149."},{"key":"e_1_2_1_69_1","unstructured":"Elad Hazan and Tomer Koren. 2012. Linear regression with limited observation. arXiv:1206.4678. Retrieved from https:\/\/arxiv.org\/abs\/1206.4678. Elad Hazan and Tomer Koren. 2012. Linear regression with limited observation. arXiv:1206.4678. Retrieved from https:\/\/arxiv.org\/abs\/1206.4678."},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1972.1054846"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177693334"},{"key":"e_1_2_1_74_1","first-page":"107","article-title":"Computing on data streams.External Mem","volume":"50","author":"Henzinger Monika Rauch","year":"1998","unstructured":"Monika Rauch Henzinger , Prabhakar Raghavan , and Sridhar Rajagopalan . 1998 . Computing on data streams.External Mem . Algor. 50 (1998), 107 \u2013 118 . Monika Rauch Henzinger, Prabhakar Raghavan, and Sridhar Rajagopalan. 1998. Computing on data streams.External Mem. Algor. 50 (1998), 107\u2013118.","journal-title":"Algor."},{"key":"e_1_2_1_75_1","volume-title":"Proceedings of the NIPS Deep Learning and Representation Learning Workshop.","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeffrey Dean . 2015 . Distilling the knowledge in a neural network . In Proceedings of the NIPS Deep Learning and Representation Learning Workshop. Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the knowledge in a neural network. In Proceedings of the NIPS Deep Learning and Representation Learning Workshop."},{"key":"e_1_2_1_76_1","volume-title":"Salakhutdinov","author":"Hinton Geoffrey E.","year":"2012","unstructured":"Geoffrey E. Hinton , Nitish Srivastava , Alex Krizhevsky , Ilya Sutskever , and Ruslan R . Salakhutdinov . 2012 . Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580. Retrieved from https:\/\/arxiv.org\/abs\/1207.0580. Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R. Salakhutdinov. 2012. Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580. Retrieved from https:\/\/arxiv.org\/abs\/1207.0580."},{"key":"e_1_2_1_77_1","volume-title":"Fahlman","author":"Hoehfeld Markus","year":"1991","unstructured":"Markus Hoehfeld and Scott E . Fahlman . 1991 . Learning with Limited Numerical Precision Using the Cascade-correlation Algorithm. Citeseer . Markus Hoehfeld and Scott E. Fahlman. 1991. Learning with Limited Numerical Precision Using the Cascade-correlation Algorithm. Citeseer."},{"key":"e_1_2_1_78_1","volume-title":"Proceedings of the 1st International Forum on Applications of Neural Networks to Power Systems. IEEE, 237\u2013241","author":"Holt J. L.","year":"1991","unstructured":"J. L. Holt and Jenq-Neng Hwang . 1991 . Finite precision error analysis for neural network learning . In Proceedings of the 1st International Forum on Applications of Neural Networks to Power Systems. IEEE, 237\u2013241 . J. L. Holt and Jenq-Neng Hwang. 1991. Finite precision error analysis for neural network learning. In Proceedings of the 1st International Forum on Applications of Neural Networks to Power Systems. IEEE, 237\u2013241."},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_2_1_80_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. 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:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861. 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:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_1_81_1","volume-title":"Dhillon","author":"Hsieh Cho-Jui","year":"2014","unstructured":"Cho-Jui Hsieh , Si Si , and Inderjit S . Dhillon . 2014 . Fast prediction for large-scale kernel machines. In Advances in Neural Information Processing Systems . 3689\u20133697. Cho-Jui Hsieh, Si Si, and Inderjit S. Dhillon. 2014. Fast prediction for large-scale kernel machines. In Advances in Neural Information Processing Systems. 3689\u20133697."},{"key":"e_1_2_1_82_1","volume-title":"Proceedings of the 3rd International Workshop on Deep Learning for Mobile Systems and Applications. 13\u201318","author":"Hu Zhiming","year":"2019","unstructured":"Zhiming Hu , Ahmad Bisher Tarakji , Vishal Raheja , Caleb Phillips , Teng Wang , and Iqbal Mohomed . 2019 . Deephome: Distributed inference with heterogeneous devices in the edge . In Proceedings of the 3rd International Workshop on Deep Learning for Mobile Systems and Applications. 13\u201318 . Zhiming Hu, Ahmad Bisher Tarakji, Vishal Raheja, Caleb Phillips, Teng Wang, and Iqbal Mohomed. 2019. Deephome: Distributed inference with heterogeneous devices in the edge. In Proceedings of the 3rd International Workshop on Deep Learning for Mobile Systems and Applications. 13\u201318."},{"key":"e_1_2_1_83_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Huang Gao","unstructured":"Gao Huang , Danlu Chen , Tianhong Li , Felix Wu , Laurens van der Maaten, and Kilian Q Weinberger. 2018. Multi-scale dense networks for resource efficient image classification . In Proceedings of the International Conference on Learning Representations (ICLR\u201918) . Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, and Kilian Q Weinberger. 2018. Multi-scale dense networks for resource efficient image classification. In Proceedings of the International Conference on Learning Representations (ICLR\u201918)."},{"key":"e_1_2_1_84_1","volume-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR\u201918)","author":"Huang Gao","unstructured":"Gao Huang , Shichen Liu , Laurens Van der Maaten , and Kilian Q. Weinberger . 2018. Condensenet: An efficient densenet using learned group convolutions . In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR\u201918) . Gao Huang, Shichen Liu, Laurens Van der Maaten, and Kilian Q. Weinberger. 2018. Condensenet: An efficient densenet using learned group convolutions. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR\u201918)."},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_2_1_86_1","volume-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size. arXiv:1602.07360.","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 <0.5 mb model size. arXiv:1602.07360. Retrieved from https:\/\/arxiv.org\/abs\/1602.07360. 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:1602.07360. Retrieved from https:\/\/arxiv.org\/abs\/1602.07360."},{"key":"e_1_2_1_87_1","unstructured":"Andrey Ignatov Radu Timofte Przemyslaw Szczepaniak William Chou Ke Wang Max Wu Tim Hartley and Luc Van Gool. 2018. AI benchmark: Running deep neural networks on Android smartphones. arXiv:1810.01109. Retrieved from https:\/\/arxiv.org\/abs\/1810.01109. Andrey Ignatov Radu Timofte Przemyslaw Szczepaniak William Chou Ke Wang Max Wu Tim Hartley and Luc Van Gool. 2018. AI benchmark: Running deep neural networks on Android smartphones. arXiv:1810.01109. Retrieved from https:\/\/arxiv.org\/abs\/1810.01109."},{"key":"e_1_2_1_88_1","unstructured":"Shinji Ito Daisuke Hatano Hanna Sumita Akihiro Yabe Takuro Fukunaga Naonori Kakimura and Ken-Ichi Kawarabayashi. 2017. Efficient sublinear-regret algorithms for online sparse linear regression with limited observation. In Advances in Neural Information Processing Systems. 4099\u20134108. Shinji Ito Daisuke Hatano Hanna Sumita Akihiro Yabe Takuro Fukunaga Naonori Kakimura and Ken-Ichi Kawarabayashi. 2017. Efficient sublinear-regret algorithms for online sparse linear regression with limited observation. In Advances in Neural Information Processing Systems. 4099\u20134108."},{"key":"e_1_2_1_89_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics. 1599\u20131607","author":"Ito Shinji","year":"2018","unstructured":"Shinji Ito , Daisuke Hatano , Hanna Sumita , Akihiro Yabe , Takuro Fukunaga , Naonori Kakimura , and Ken-Ichi Kawarabayashi . 2018 . Online regression with partial information: Generalization and linear projection . In Proceedings of the International Conference on Artificial Intelligence and Statistics. 1599\u20131607 . Shinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, and Ken-Ichi Kawarabayashi. 2018. Online regression with partial information: Generalization and linear projection. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 1599\u20131607."},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"e_1_2_1_92_1","volume-title":"Proceedings of the International Conference on Machine Learning. 486\u2013494","author":"Jose Cijo","year":"2013","unstructured":"Cijo Jose , Prasoon Goyal , Parv Aggrwal , and Manik Varma . 2013 . Local deep kernel learning for efficient non-linear svm prediction . In Proceedings of the International Conference on Machine Learning. 486\u2013494 . Cijo Jose, Prasoon Goyal, Parv Aggrwal, and Manik Varma. 2013. Local deep kernel learning for efficient non-linear svm prediction. In Proceedings of the International Conference on Machine Learning. 486\u2013494."},{"key":"e_1_2_1_93_1","volume-title":"Raquel Urtasun, and Andreas Moshovos.","author":"Judd Patrick","year":"2015","unstructured":"Patrick Judd , Jorge Albericio , Tayler Hetherington , Tor Aamodt , Natalie Enright Jerger , Raquel Urtasun, and Andreas Moshovos. 2015 . Reduced-precision strategies for bounded memory in deep neural nets. arXiv:1511.05236. Retrieved from https:\/\/arxiv.org\/abs\/1511.05236. Patrick Judd, Jorge Albericio, Tayler Hetherington, Tor Aamodt, Natalie Enright Jerger, Raquel Urtasun, and Andreas Moshovos. 2015. Reduced-precision strategies for bounded memory in deep neural nets. arXiv:1511.05236. Retrieved from https:\/\/arxiv.org\/abs\/1511.05236."},{"key":"e_1_2_1_94_1","volume-title":"The Computational Complexity of Machine Learning","author":"Kearns Michael J.","unstructured":"Michael J. Kearns . 1990. The Computational Complexity of Machine Learning . MIT Press . Michael J. Kearns. 1990. The Computational Complexity of Machine Learning. MIT Press."},{"key":"e_1_2_1_95_1","unstructured":"Minje Kim and Paris Smaragdis. 2016. Bitwise neural networks. arXiv:1601.06071. Retrieved from https:\/\/arxiv.org\/abs\/1601.06071. Minje Kim and Paris Smaragdis. 2016. Bitwise neural networks. arXiv:1601.06071. Retrieved from https:\/\/arxiv.org\/abs\/1601.06071."},{"key":"e_1_2_1_96_1","volume-title":"Proceedings of the 5th International Conference on Microelectronics for Neural Networks. IEEE, 149\u2013156","author":"Kollmann Kuno","year":"1996","unstructured":"Kuno Kollmann , K.-R. Riemschneider , and Hans Christoph Zeidler . 1996 . On-chip backpropagation training using parallel stochastic bit streams . In Proceedings of the 5th International Conference on Microelectronics for Neural Networks. IEEE, 149\u2013156 . Kuno Kollmann, K.-R. Riemschneider, and Hans Christoph Zeidler. 1996. On-chip backpropagation training using parallel stochastic bit streams. In Proceedings of the 5th International Conference on Microelectronics for Neural Networks. IEEE, 149\u2013156."},{"key":"e_1_2_1_97_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E . Hinton . 2012 . Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems . 1097\u20131105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. 1097\u20131105."},{"key":"e_1_2_1_98_1","volume-title":"Proceedings of the 2012 International Conference on Data Science & Engineering (ICDSE\u201912)","author":"Vrushali","unstructured":"Vrushali Y. Kulkarni and Pradeep K. Sinha. 2012. Pruning of random forest classifiers: A survey and future directions . In Proceedings of the 2012 International Conference on Data Science & Engineering (ICDSE\u201912) . IEEE, 64\u201368. Vrushali Y. Kulkarni and Pradeep K. Sinha. 2012. Pruning of random forest classifiers: A survey and future directions. In Proceedings of the 2012 International Conference on Data Science & Engineering (ICDSE\u201912). IEEE, 64\u201368."},{"key":"e_1_2_1_99_1","volume-title":"Proceedings of the International Conference on Machine Learning. 1935\u20131944","author":"Kumar Ashish","year":"2017","unstructured":"Ashish Kumar , Saurabh Goyal , and Manik Varma . 2017 . Resource-efficient machine learning in 2 KB RAM for the Internet of Things . In Proceedings of the International Conference on Machine Learning. 1935\u20131944 . Ashish Kumar, Saurabh Goyal, and Manik Varma. 2017. Resource-efficient machine learning in 2 KB RAM for the Internet of Things. In Proceedings of the International Conference on Machine Learning. 1935\u20131944."},{"key":"e_1_2_1_100_1","volume-title":"Proceedings of the International Conference on Machine Learning. 622\u2013630","author":"Kusner Matt","year":"2014","unstructured":"Matt Kusner , Stephen Tyree , Kilian Weinberger , and Kunal Agrawal . 2014 . Stochastic neighbor compression . In Proceedings of the International Conference on Machine Learning. 622\u2013630 . Matt Kusner, Stephen Tyree, Kilian Weinberger, and Kunal Agrawal. 2014. Stochastic neighbor compression. In Proceedings of the International Conference on Machine Learning. 622\u2013630."},{"key":"e_1_2_1_101_1","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/S0019-9958(79)90402-9","article-title":"Compound hypothesis testing with finite memory","volume":"40","author":"Lakshmanan K. B.","year":"1979","unstructured":"K. B. Lakshmanan and B. Chandrasekaran . 1979 . Compound hypothesis testing with finite memory . Inf. Contr. 40 , 2 (1979), 223 \u2013 233 . K. B. Lakshmanan and B. Chandrasekaran. 1979. Compound hypothesis testing with finite memory. Inf. Contr. 40, 2 (1979), 223\u2013233.","journal-title":"Inf. Contr."},{"key":"e_1_2_1_102_1","volume-title":"Sparse online learning via truncated gradient. J. Mach. Learn. Res. 10 (Mar","author":"Langford John","year":"2009","unstructured":"John Langford , Lihong Li , and Tong Zhang . 2009. Sparse online learning via truncated gradient. J. Mach. Learn. Res. 10 (Mar . 2009 ), 777\u2013801. John Langford, Lihong Li, and Tong Zhang. 2009. Sparse online learning via truncated gradient. J. Mach. Learn. Res. 10 (Mar. 2009), 777\u2013801."},{"key":"e_1_2_1_103_1","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"85","author":"Le Quoc","year":"2013","unstructured":"Quoc Le , Tam\u00e1s Sarl\u00f3s , and Alex Smola . 2013 . Fastfood-approximating kernel expansions in loglinear time . In Proceedings of the International Conference on Machine Learning , Vol. 85 . Quoc Le, Tam\u00e1s Sarl\u00f3s, and Alex Smola. 2013. Fastfood-approximating kernel expansions in loglinear time. In Proceedings of the International Conference on Machine Learning, Vol. 85."},{"key":"e_1_2_1_104_1","volume-title":"Retrieved","author":"Learn Scikit","year":"2020","unstructured":"Scikit Learn . Decision Tree . Retrieved December 22, 2020 from http:\/\/scikit-learn.org\/stable\/modules\/tree.html#complexity. Scikit Learn. Decision Tree. Retrieved December 22, 2020 from http:\/\/scikit-learn.org\/stable\/modules\/tree.html#complexity."},{"key":"e_1_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"e_1_2_1_106_1","volume-title":"Proceedings of the 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT\u201916)","author":"Lee Jongmin","year":"2016","unstructured":"Jongmin Lee , Michael Stanley , Andreas Spanias , and Cihan Tepedelenlioglu . 2016 . Integrating machine learning in embedded sensor systems for internet-of-things applications . In Proceedings of the 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT\u201916) . IEEE, 290\u2013294. Jongmin Lee, Michael Stanley, Andreas Spanias, and Cihan Tepedelenlioglu. 2016. Integrating machine learning in embedded sensor systems for internet-of-things applications. In Proceedings of the 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT\u201916). IEEE, 290\u2013294."},{"key":"e_1_2_1_107_1","volume-title":"Proceedings of the 17th Conference on Embedded Networked Sensor Systems. 138\u2013152","author":"Lee Seulki","year":"2019","unstructured":"Seulki Lee and Shahriar Nirjon . 2019 . Neuro. ZERO: A zero-energy neural network accelerator for embedded sensing and inference systems . In Proceedings of the 17th Conference on Embedded Networked Sensor Systems. 138\u2013152 . Seulki Lee and Shahriar Nirjon. 2019. Neuro. ZERO: A zero-energy neural network accelerator for embedded sensing and inference systems. In Proceedings of the 17th Conference on Embedded Networked Sensor Systems. 138\u2013152."},{"key":"e_1_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1986.1057250"},{"key":"e_1_2_1_109_1","unstructured":"Chun-Liang Li Hsuan-Tien Lin and Chi-Jen Lu. 2016. Rivalry of two families of algorithms for memory-restricted streaming pca. In Artificial Intelligence and Statistics. 473\u2013481. Chun-Liang Li Hsuan-Tien Lin and Chi-Jen Lu. 2016. Rivalry of two families of algorithms for memory-restricted streaming pca. In Artificial Intelligence and Statistics. 473\u2013481."},{"key":"e_1_2_1_110_1","unstructured":"Hao Li Soham De Zheng Xu Christoph Studer Hanan Samet and Tom Goldstein. 2017. Training quantized nets: A deeper understanding. In Advances in Neural Information Processing Systems. 5811\u20135821. Hao Li Soham De Zheng Xu Christoph Studer Hanan Samet and Tom Goldstein. 2017. Training quantized nets: A deeper understanding. In Advances in Neural Information Processing Systems. 5811\u20135821."},{"key":"e_1_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_2_1_112_1","unstructured":"Xiang Li Tao Qin Jian Yang and Tieyan Liu. 2016. LightRNN: Memory and computation-efficient recurrent neural networks. In Advances in Neural Information Processing Systems. 4385\u20134393. Xiang Li Tao Qin Jian Yang and Tieyan Liu. 2016. LightRNN: Memory and computation-efficient recurrent neural networks. In Advances in Neural Information Processing Systems. 4385\u20134393."},{"key":"e_1_2_1_113_1","volume-title":"De Sa","author":"Li Zheng","year":"2019","unstructured":"Zheng Li and Christopher M . De Sa . 2019 . Dimension-free bounds for low-precision training. In Advances in Neural Information Processing Systems . 11728\u201311738. Zheng Li and Christopher M. De Sa. 2019. Dimension-free bounds for low-precision training. In Advances in Neural Information Processing Systems. 11728\u201311738."},{"key":"e_1_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007608224229"},{"key":"e_1_2_1_115_1","volume-title":"Dinh Thai Hoang, Yutao Jiao, Ying-Chang Liang, Qiang Yang, Dusit Niyato, and Chunyan Miao.","author":"Bryan Lim Wei Yang","year":"2020","unstructured":"Wei Yang Bryan Lim , Nguyen Cong Luong , Dinh Thai Hoang, Yutao Jiao, Ying-Chang Liang, Qiang Yang, Dusit Niyato, and Chunyan Miao. 2020 . Federated learning in mobile edge networks: A comprehensive survey. IEEE Commun. Surv. Tutor . (2020). Wei Yang Bryan Lim, Nguyen Cong Luong, Dinh Thai Hoang, Yutao Jiao, Ying-Chang Liang, Qiang Yang, Dusit Niyato, and Chunyan Miao. 2020. Federated learning in mobile edge networks: A comprehensive survey. IEEE Commun. Surv. Tutor. (2020)."},{"key":"e_1_2_1_116_1","unstructured":"Yujun Lin Song Han Huizi Mao Yu Wang and William J Dally. 2017. Deep gradient compression: Reducing the communication bandwidth for distributed training. arXiv:1712.01887. Retrieved from https:\/\/arxiv.org\/abs\/1712.01887. Yujun Lin Song Han Huizi Mao Yu Wang and William J Dally. 2017. Deep gradient compression: Reducing the communication bandwidth for distributed training. arXiv:1712.01887. Retrieved from https:\/\/arxiv.org\/abs\/1712.01887."},{"key":"e_1_2_1_117_1","unstructured":"Zhouhan Lin Matthieu Courbariaux Roland Memisevic and Yoshua Bengio. 2015. Neural networks with few multiplications. arXiv:1510.03009. Retrieved from https:\/\/arxiv.org\/abs\/1510.03009. Zhouhan Lin Matthieu Courbariaux Roland Memisevic and Yoshua Bengio. 2015. Neural networks with few multiplications. arXiv:1510.03009. Retrieved from https:\/\/arxiv.org\/abs\/1510.03009."},{"key":"e_1_2_1_118_1","volume-title":"Proceedings of the Asia Information Retrieval Symposium. Springer, 502\u2013513","author":"Lin Ziheng","year":"2010","unstructured":"Ziheng Lin , Yan Gu , and Samarjit Chakraborty . 2010 . Tuning machine-learning algorithms for battery-operated portable devices . In Proceedings of the Asia Information Retrieval Symposium. Springer, 502\u2013513 . Ziheng Lin, Yan Gu, and Samarjit Chakraborty. 2010. Tuning machine-learning algorithms for battery-operated portable devices. In Proceedings of the Asia Information Retrieval Symposium. Springer, 502\u2013513."},{"key":"e_1_2_1_119_1","unstructured":"Jiayi Liu Samarth Tripathi Unmesh Kurup and Mohak Shah. 2020. Pruning algorithms to accelerate convolutional neural networks for edge applications: A survey. arXiv:2005.04275. Retrieved from https:\/\/arxiv.org\/abs\/2005.04275. Jiayi Liu Samarth Tripathi Unmesh Kurup and Mohak Shah. 2020. Pruning algorithms to accelerate convolutional neural networks for edge applications: A survey. arXiv:2005.04275. Retrieved from https:\/\/arxiv.org\/abs\/2005.04275."},{"key":"e_1_2_1_120_1","volume-title":"Proceedings of the 2017 ACM on Multimedia Conference. ACM, 1663\u20131671","author":"Lu Zongqing","year":"2017","unstructured":"Zongqing Lu , Swati Rallapalli , Kevin Chan , and Thomas La Porta . 2017 . Modeling the resource requirements of convolutional neural networks on mobile devices . In Proceedings of the 2017 ACM on Multimedia Conference. ACM, 1663\u20131671 . Zongqing Lu, Swati Rallapalli, Kevin Chan, and Thomas La Porta. 2017. Modeling the resource requirements of convolutional neural networks on mobile devices. In Proceedings of the 2017 ACM on Multimedia Conference. ACM, 1663\u20131671."},{"key":"e_1_2_1_122_1","volume-title":"Proceedings of the 3rd International Conference on Electronics, Circuits, and Systems","volume":"1","author":"Magoulas G. D.","unstructured":"G. D. Magoulas , M. N. Vrahatis , and G. S. Androulakis . 1996. A new method in neural network supervised training with imprecision . In Proceedings of the 3rd International Conference on Electronics, Circuits, and Systems , Vol. 1 . IEEE, 287\u2013290. G. D. Magoulas, M. N. Vrahatis, and G. S. Androulakis. 1996. A new method in neural network supervised training with imprecision. In Proceedings of the 3rd International Conference on Electronics, Circuits, and Systems, Vol. 1. IEEE, 287\u2013290."},{"key":"e_1_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3371154"},{"key":"e_1_2_1_124_1","doi-asserted-by":"crossref","unstructured":"Diana Marculescu Dimitrios Stamoulis and Ermao Cai. 2018. Hardware-aware machine learning: Modeling and optimization. arXiv:1809.05476. Retrieved from https:\/\/arxiv.org\/abs\/1809.05476. Diana Marculescu Dimitrios Stamoulis and Ermao Cai. 2018. Hardware-aware machine learning: Modeling and optimization. arXiv:1809.05476. Retrieved from https:\/\/arxiv.org\/abs\/1809.05476.","DOI":"10.1145\/3240765.3243479"},{"key":"e_1_2_1_125_1","volume-title":"RATQ: A universal fixed-length quantizer for stochastic optimization. arxiv:cs.LG\/1908.08200.","author":"Mayekar Prathamesh","year":"2019","unstructured":"Prathamesh Mayekar and Himanshu Tyagi . 2019 . RATQ: A universal fixed-length quantizer for stochastic optimization. arxiv:cs.LG\/1908.08200. Retrieved from https:\/\/arxiv.org\/abs\/1908.08200. Prathamesh Mayekar and Himanshu Tyagi. 2019. RATQ: A universal fixed-length quantizer for stochastic optimization. arxiv:cs.LG\/1908.08200. Retrieved from https:\/\/arxiv.org\/abs\/1908.08200."},{"key":"e_1_2_1_126_1","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.ifacol.2018.11.063","article-title":"A survey of the implementation of linear model predictive control on fpgas","volume":"51","author":"McInerney Ian","year":"2018","unstructured":"Ian McInerney , George A. Constantinides , and Eric C. Kerrigan . 2018 . A survey of the implementation of linear model predictive control on fpgas . IFAC-PapersOnLine 51 , 20 (2018), 381 \u2013 387 . Ian McInerney, George A. Constantinides, and Eric C. Kerrigan. 2018. A survey of the implementation of linear model predictive control on fpgas. IFAC-PapersOnLine 51, 20 (2018), 381\u2013387.","journal-title":"IFAC-PapersOnLine"},{"key":"e_1_2_1_127_1","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics. 1273\u20131282. Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics. 1273\u20131282."},{"key":"e_1_2_1_128_1","unstructured":"H. Brendan McMahan Eider Moore Daniel Ramage and Blaise Ag\u00fcera y Arcas. 2016. Federated learning of deep networks using model averaging. arxiv:1602.05629. Retrieved fromhttp:\/\/arxiv.org\/abs\/1602.05629. H. Brendan McMahan Eider Moore Daniel Ramage and Blaise Ag\u00fcera y Arcas. 2016. Federated learning of deep networks using model averaging. arxiv:1602.05629. Retrieved fromhttp:\/\/arxiv.org\/abs\/1602.05629."},{"key":"e_1_2_1_129_1","volume-title":"et\u00a0al","author":"Micikevicius Paulius","year":"2017","unstructured":"Paulius Micikevicius , Sharan Narang , Jonah Alben , Gregory Diamos , Erich Elsen , David Garcia , Boris Ginsburg , Michael Houston , Oleksii Kuchaev , Ganesh Venkatesh , et\u00a0al . 2017 . Mixed precision training. arXiv:1710.03740. Retrieved from https:\/\/arxiv.org\/abs\/1710.03740. Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaev, Ganesh Venkatesh, et\u00a0al. 2017. Mixed precision training. arXiv:1710.03740. Retrieved from https:\/\/arxiv.org\/abs\/1710.03740."},{"key":"e_1_2_1_130_1","unstructured":"Shervin Minaee Yuri Boykov Fatih Porikli Antonio Plaza Nasser Kehtarnavaz and Demetri Terzopoulos. 2020. Image segmentation using deep learning: A survey. arXiv:2001.05566. Retrieved from https:\/\/arxiv.org\/abs\/2001.05566. Shervin Minaee Yuri Boykov Fatih Porikli Antonio Plaza Nasser Kehtarnavaz and Demetri Terzopoulos. 2020. Image segmentation using deep learning: A survey. arXiv:2001.05566. Retrieved from https:\/\/arxiv.org\/abs\/2001.05566."},{"key":"e_1_2_1_131_1","unstructured":"Ioannis Mitliagkas Constantine Caramanis and Prateek Jain. 2013. Memory limited streaming PCA. In Advances in Neural Information Processing Systems. 2886\u20132894. Ioannis Mitliagkas Constantine Caramanis and Prateek Jain. 2013. Memory limited streaming PCA. In Advances in Neural Information Processing Systems. 2886\u20132894."},{"key":"e_1_2_1_132_1","volume-title":"Foundations of Machine Learning","author":"Mohri Mehryar","unstructured":"Mehryar Mohri , Afshin Rostamizadeh , and Ameet Talwalkar . 2012. Foundations of Machine Learning . MIT Press . Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. 2012. Foundations of Machine Learning. MIT Press."},{"key":"e_1_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.1145\/359619.359627"},{"key":"e_1_2_1_134_1","volume-title":"Conference on Learning Theory. 1516\u20131566","author":"Moshkovitz Dana","year":"2017","unstructured":"Dana Moshkovitz and Michal Moshkovitz . 2017 . Mixing implies lower bounds for space bounded learning . In Conference on Learning Theory. 1516\u20131566 . Dana Moshkovitz and Michal Moshkovitz. 2017. Mixing implies lower bounds for space bounded learning. In Conference on Learning Theory. 1516\u20131566."},{"key":"e_1_2_1_135_1","volume-title":"LIPIcs-Leibniz International Proceedings in Informatics","volume":"94","author":"Moshkovitz Dana","year":"2018","unstructured":"Dana Moshkovitz and Michal Moshkovitz . 2018 . Entropy samplers and strong generic lower bounds for space bounded learning . In LIPIcs-Leibniz International Proceedings in Informatics , Vol. 94 . Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik. Dana Moshkovitz and Michal Moshkovitz. 2018. Entropy samplers and strong generic lower bounds for space bounded learning. In LIPIcs-Leibniz International Proceedings in Informatics, Vol. 94. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik."},{"key":"e_1_2_1_136_1","doi-asserted-by":"crossref","unstructured":"Michal Moshkovitz and Naftali Tishby. 2017. A general memory-bounded learning algorithm. arXiv:1712.03524. Retrieved from https:\/\/arxiv.org\/abs\/1712.03524. Michal Moshkovitz and Naftali Tishby. 2017. A general memory-bounded learning algorithm. arXiv:1712.03524. Retrieved from https:\/\/arxiv.org\/abs\/1712.03524.","DOI":"10.1007\/978-981-287-588-4_100717"},{"key":"e_1_2_1_137_1","unstructured":"Tomoya Murata and Taiji Suzuki. 2018. Sample efficient stochastic gradient iterative hard thresholding method for stochastic sparse linear regression with limited attribute observation. In Advances in Neural Information Processing Systems. 5317\u20135326. Tomoya Murata and Taiji Suzuki. 2018. Sample efficient stochastic gradient iterative hard thresholding method for stochastic sparse linear regression with limited attribute observation. In Advances in Neural Information Processing Systems. 5317\u20135326."},{"key":"e_1_2_1_138_1","unstructured":"M. G. Murshed Christopher Murphy Daqing Hou Nazar Khan Ganesh Ananthanarayanan and Faraz Hussain. 2019. Machine learning at the network edge: A survey. arXiv:1908.00080. Retrieved from https:\/\/arxiv.org\/abs\/1908.00080. M. G. Murshed Christopher Murphy Daqing Hou Nazar Khan Ganesh Ananthanarayanan and Faraz Hussain. 2019. Machine learning at the network edge: A survey. arXiv:1908.00080. Retrieved from https:\/\/arxiv.org\/abs\/1908.00080."},{"key":"e_1_2_1_139_1","volume-title":"Retrieved","author":"Net Apache","year":"2020","unstructured":"Apache MX Net . Memory cost of deep nets under different allocations . Retrieved December 22, 2020 https:\/\/github.com\/apache\/incubator-mxnet\/tree\/master\/example\/memcost#memory-cost-of-deep-nets-under-different-allocations. Apache MXNet. Memory cost of deep nets under different allocations. Retrieved December 22, 2020 https:\/\/github.com\/apache\/incubator-mxnet\/tree\/master\/example\/memcost#memory-cost-of-deep-nets-under-different-allocations."},{"key":"e_1_2_1_140_1","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","author":"Nesterov Yurii","unstructured":"Yurii Nesterov . 2013. Introductory Lectures on Convex Optimization: A Basic Course . Vol. 87 . Springer Science & Business Media . Yurii Nesterov. 2013. Introductory Lectures on Convex Optimization: A Basic Course. Vol. 87. Springer Science & Business Media."},{"key":"e_1_2_1_141_1","volume-title":"Usability heuristics","author":"Nielsen Jakob","unstructured":"Jakob Nielsen . 1993. Usability heuristics . In Usability Engineering, Jakob Nielsen (Ed.). Morgan Kaufmann , San Francisco, CA , 115\u2013163.DOI:https:\/\/doi.org\/10.1016\/B978-0-08-052029-2.50008-5 Jakob Nielsen. 1993. Usability heuristics. In Usability Engineering, Jakob Nielsen (Ed.). Morgan Kaufmann, San Francisco, CA, 115\u2013163.DOI:https:\/\/doi.org\/10.1016\/B978-0-08-052029-2.50008-5"},{"key":"e_1_2_1_142_1","volume-title":"Paleo: A performance model for deep neural networks.","author":"Qi Hang","year":"2016","unstructured":"Hang Qi , Evan R. Sparks , and Ameet Talwalkar . 2016 . Paleo: A performance model for deep neural networks. Hang Qi, Evan R. Sparks, and Ameet Talwalkar. 2016. Paleo: A performance model for deep neural networks."},{"key":"e_1_2_1_143_1","volume-title":"Ross Girshick, Kaiming He, and Piotr Doll\u00e1r.","author":"Radosavovic Ilija","year":"2020","unstructured":"Ilija Radosavovic , Raj Prateek Kosaraju , Ross Girshick, Kaiming He, and Piotr Doll\u00e1r. 2020 . Designing network design spaces. arXiv:2003.13678. Retrieved from https:\/\/arxiv.org\/abs\/2003.13678. Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, and Piotr Doll\u00e1r. 2020. Designing network design spaces. arXiv:2003.13678. Retrieved from https:\/\/arxiv.org\/abs\/2003.13678."},{"key":"e_1_2_1_144_1","volume-title":"Proceedings of the European Conference on Computer Vision. Springer, 525\u2013542","author":"Rastegari Mohammad","year":"2016","unstructured":"Mohammad Rastegari , Vicente Ordonez , Joseph Redmon , and Ali Farhadi . 2016 . Xnor-net: Imagenet classification using binary convolutional neural networks . In Proceedings of the European Conference on Computer Vision. Springer, 525\u2013542 . Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. 2016. Xnor-net: Imagenet classification using binary convolutional neural networks. In Proceedings of the European Conference on Computer Vision. Springer, 525\u2013542."},{"key":"e_1_2_1_145_1","volume-title":"Projectionnet: Learning efficient on-device deep networks using neural projections. arXiv:1708.00630.","author":"Ravi Sujith","year":"2017","unstructured":"Sujith Ravi . 2017 . Projectionnet: Learning efficient on-device deep networks using neural projections. arXiv:1708.00630. Retrieved from https:\/\/arxiv.org\/abs\/1708.00630. Sujith Ravi. 2017. Projectionnet: Learning efficient on-device deep networks using neural projections. arXiv:1708.00630. Retrieved from https:\/\/arxiv.org\/abs\/1708.00630."},{"key":"e_1_2_1_146_1","volume-title":"Proceedings of the 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS\u201917)","author":"Raz Ran","year":"2017","unstructured":"Ran Raz . 2017 . A time-space lower bound for a large class of learning problems . In Proceedings of the 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS\u201917) . IEEE, 732\u2013742. Ran Raz. 2017. A time-space lower bound for a large class of learning problems. In Proceedings of the 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS\u201917). IEEE, 732\u2013742."},{"key":"e_1_2_1_147_1","volume-title":"Retrieved","author":"Research Baidu","year":"2020","unstructured":"Baidu Research . Benchmarking deep learning operations on different hardwares . Retrieved December 22, 2020 from https:\/\/github.com\/baidu-research\/DeepBench. Baidu Research. Benchmarking deep learning operations on different hardwares. Retrieved December 22, 2020 from https:\/\/github.com\/baidu-research\/DeepBench."},{"key":"e_1_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"e_1_2_1_149_1","unstructured":"Crefeda Faviola Rodrigues Graham Riley and Mikel Luj\u00e1n. 2018. Fine-grained energy and performance profiling framework for deep convolutional neural networks. arXiv:1803.11151. Retrieved from https:\/\/arxiv.org\/abs\/1803.11151. Crefeda Faviola Rodrigues Graham Riley and Mikel Luj\u00e1n. 2018. Fine-grained energy and performance profiling framework for deep convolutional neural networks. arXiv:1803.11151. Retrieved from https:\/\/arxiv.org\/abs\/1803.11151."},{"key":"e_1_2_1_150_1","volume-title":"Proceedings of the 2016 International Symposium on Low Power Electronics and Design. ACM, 112\u2013117","author":"Rouhani Bita Darvish","year":"2016","unstructured":"Bita Darvish Rouhani , Azalia Mirhoseini , and Farinaz Koushanfar . 2016 . Delight: Adding energy dimension to deep neural networks . In Proceedings of the 2016 International Symposium on Low Power Electronics and Design. ACM, 112\u2013117 . Bita Darvish Rouhani, Azalia Mirhoseini, and Farinaz Koushanfar. 2016. Delight: Adding energy dimension to deep neural networks. In Proceedings of the 2016 International Symposium on Low Power Electronics and Design. ACM, 112\u2013117."},{"key":"e_1_2_1_151_1","volume-title":"Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201917)","author":"Rouhani Bita Darvish","year":"2017","unstructured":"Bita Darvish Rouhani , Azalia Mirhoseini , and Farinaz Koushanfar . 2017 . TinyDL: Just-in-time deep learning solution for constrained embedded systems . In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201917) . 1\u20134. Bita Darvish Rouhani, Azalia Mirhoseini, and Farinaz Koushanfar. 2017. TinyDL: Just-in-time deep learning solution for constrained embedded systems. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS\u201917). 1\u20134."},{"key":"e_1_2_1_152_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-007-0037-z"},{"key":"e_1_2_1_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1999.1666"},{"key":"e_1_2_1_155_1","volume-title":"Understanding Machine Learning: From Theory to Algorithms","author":"Shalev-Shwartz Shai","unstructured":"Shai Shalev-Shwartz and Shai Ben-David . 2014. Understanding Machine Learning: From Theory to Algorithms . Cambridge University Press . Shai Shalev-Shwartz and Shai Ben-David. 2014. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press."},{"key":"e_1_2_1_156_1","unstructured":"Shai Shalev-Shwartz Ohad Shamir and Eran Tromer. 2012. Using more data to speed-up training time. In Artificial Intelligence and Statistics. 1019\u20131027. Shai Shalev-Shwartz Ohad Shamir and Eran Tromer. 2012. Using more data to speed-up training time. In Artificial Intelligence and Statistics. 1019\u20131027."},{"key":"e_1_2_1_157_1","unstructured":"Ohad Shamir. 2014. Fundamental limits of online and distributed algorithms for statistical learning and estimation. In Advances in Neural Information Processing Systems. 163\u2013171. Ohad Shamir. 2014. Fundamental limits of online and distributed algorithms for statistical learning and estimation. In Advances in Neural Information Processing Systems. 163\u2013171."},{"key":"e_1_2_1_158_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Retrieved from https:\/\/arxiv.org\/abs\/1409.1556. Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Retrieved from https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_2_1_159_1","unstructured":"Daniel Soudry Itay Hubara and Ron Meir. 2014. Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights. In Advances in Neural Information Processing Systems. 963\u2013971. Daniel Soudry Itay Hubara and Ron Meir. 2014. Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights. In Advances in Neural Information Processing Systems. 963\u2013971."},{"key":"e_1_2_1_160_1","volume-title":"Proceedings of the NIPS Workshop on Computataional Trade-offs in Statistical Learning.","author":"Srebro Nathan","year":"2011","unstructured":"Nathan Srebro and Karthik Sridharan . 2011 . Theoretical basis for \u201cmore data less work .\u201d In Proceedings of the NIPS Workshop on Computataional Trade-offs in Statistical Learning. Nathan Srebro and Karthik Sridharan. 2011. Theoretical basis for \u201cmore data less work.\u201d In Proceedings of the NIPS Workshop on Computataional Trade-offs in Statistical Learning."},{"key":"e_1_2_1_161_1","volume-title":"Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE\u201918)","author":"Stamoulis Dimitrios","year":"2018","unstructured":"Dimitrios Stamoulis , Ermao Cai , Da-Cheng Juan , and Diana Marculescu . 2018 . HyperPower: Power-and memory-constrained hyper-parameter optimization for neural networks . In Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE\u201918) . IEEE, 19\u201324. Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan, and Diana Marculescu. 2018. HyperPower: Power-and memory-constrained hyper-parameter optimization for neural networks. In Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE\u201918). IEEE, 19\u201324."},{"key":"e_1_2_1_162_1","unstructured":"Dimitrios Stamoulis Ruizhou Ding Di Wang Dimitrios Lymberopoulos Bodhi Priyantha Jie Liu and Diana Marculescu. 2019. Single-path nas: Designing hardware-efficient convnets in less than 4 hours. arXiv:1904.02877. Retrieved from https:\/\/arxiv.org\/abs\/1904.02877. Dimitrios Stamoulis Ruizhou Ding Di Wang Dimitrios Lymberopoulos Bodhi Priyantha Jie Liu and Diana Marculescu. 2019. Single-path nas: Designing hardware-efficient convnets in less than 4 hours. arXiv:1904.02877. Retrieved from https:\/\/arxiv.org\/abs\/1904.02877."},{"key":"e_1_2_1_163_1","volume-title":"Proceedings of the Conference on Learning Theory. 1564\u20131587","author":"Steinhardt Jacob","year":"2015","unstructured":"Jacob Steinhardt and John Duchi . 2015 . Minimax rates for memory-bounded sparse linear regression . In Proceedings of the Conference on Learning Theory. 1564\u20131587 . Jacob Steinhardt and John Duchi. 2015. Minimax rates for memory-bounded sparse linear regression. In Proceedings of the Conference on Learning Theory. 1564\u20131587."},{"key":"e_1_2_1_164_1","volume-title":"Proceedings of the Conference on Learning Theory. 1490\u20131516","author":"Steinhardt Jacob","year":"2016","unstructured":"Jacob Steinhardt , Gregory Valiant , and Stefan Wager . 2016 . Memory, communication, and statistical queries . In Proceedings of the Conference on Learning Theory. 1490\u20131516 . Jacob Steinhardt, Gregory Valiant, and Stefan Wager. 2016. Memory, communication, and statistical queries. In Proceedings of the Conference on Learning Theory. 1490\u20131516."},{"key":"e_1_2_1_165_1","unstructured":"Sebastian U. Stich Jean-Baptiste Cordonnier and Martin Jaggi. 2018. Sparsified SGD with memory. In Advances in Neural Information Processing Systems. 4447\u20134458. Sebastian U. Stich Jean-Baptiste Cordonnier and Martin Jaggi. 2018. Sparsified SGD with memory. In Advances in Neural Information Processing Systems. 4447\u20134458."},{"key":"e_1_2_1_166_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"e_1_2_1_167_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_2_1_168_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_1_169_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_1_170_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196930"},{"key":"e_1_2_1_171_1","volume-title":"Le","author":"Tan Mingxing","year":"2018","unstructured":"Mingxing Tan , Bo Chen , Ruoming Pang , Vijay Vasudevan , and Quoc V . Le . 2018 . MnasNet: Platform-aware neural architecture search for mobile. arXiv:1807.11626. Retrieved from https:\/\/arxiv.org\/abs\/1807.11626. Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, and Quoc V. Le. 2018. MnasNet: Platform-aware neural architecture search for mobile. arXiv:1807.11626. Retrieved from https:\/\/arxiv.org\/abs\/1807.11626."},{"key":"e_1_2_1_172_1","volume-title":"Le","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V . Le . 2019 . Efficientnet : Rethinking model scaling for convolutional neural networks. arXiv:1905.11946. Retrieved from https:\/\/arxiv.org\/abs\/1905.11946. Mingxing Tan and Quoc V. Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv:1905.11946. Retrieved from https:\/\/arxiv.org\/abs\/1905.11946."},{"key":"e_1_2_1_173_1","volume-title":"Proceedings of the British Machine Vision Conference.","author":"Tan Mingxing","unstructured":"Mingxing Tan and Quoc V. Le . 2019. Mixconv: Mixed depthwise convolutional kernels . In Proceedings of the British Machine Vision Conference. Mingxing Tan and Quoc V. Le. 2019. Mixconv: Mixed depthwise convolutional kernels. In Proceedings of the British Machine Vision Conference."},{"key":"e_1_2_1_174_1","unstructured":"Hanlin Tang Shaoduo Gan Ce Zhang Tong Zhang and Ji Liu. 2018. Communication compression for decentralized training. In Advances in Neural Information Processing Systems. 7652\u20137662. Hanlin Tang Shaoduo Gan Ce Zhang Tong Zhang and Ji Liu. 2018. Communication compression for decentralized training. In Advances in Neural Information Processing Systems. 7652\u20137662."},{"key":"e_1_2_1_175_1","unstructured":"Zhenheng Tang Shaohuai Shi Xiaowen Chu Wei Wang and Bo Li. 2020. Communication-efficient distributed deep learning: A somprehensive survey. arxiv:cs.DC\/2003.06307.. Retrieved from https:\/\/arxiv.org\/abs\/2003.06307. Zhenheng Tang Shaohuai Shi Xiaowen Chu Wei Wang and Bo Li. 2020. Communication-efficient distributed deep learning: A somprehensive survey. arxiv:cs.DC\/2003.06307.. Retrieved from https:\/\/arxiv.org\/abs\/2003.06307."},{"key":"e_1_2_1_176_1","volume-title":"Proceedings of the 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton\u201912)","author":"Tsianos Konstantinos I.","unstructured":"Konstantinos I. Tsianos , Sean Lawlor , and Michael G. Rabbat . 2012. Consensus-based distributed optimization: Practical issues and applications in large-scale machine learning . In Proceedings of the 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton\u201912) . IEEE, 1543\u20131550. Konstantinos I. Tsianos, Sean Lawlor, and Michael G. Rabbat. 2012. Consensus-based distributed optimization: Practical issues and applications in large-scale machine learning. In Proceedings of the 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton\u201912). IEEE, 1543\u20131550."},{"key":"e_1_2_1_177_1","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"e_1_2_1_178_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952564"},{"key":"e_1_2_1_179_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"e_1_2_1_180_1","volume-title":"Estimation of Dependences Based on Empirical Data","author":"Vapnik Vladimir","unstructured":"Vladimir Vapnik . 2006. Estimation of Dependences Based on Empirical Data . Springer Science & Business Media . Vladimir Vapnik. 2006. Estimation of Dependences Based on Empirical Data. Springer Science & Business Media."},{"key":"e_1_2_1_181_1","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s10994-018-5742-0","article-title":"Rethinking statistical learning theory: Learning using statistical invariants","volume":"108","author":"Vapnik Vladimir","year":"2019","unstructured":"Vladimir Vapnik and Rauf Izmailov . 2019 . Rethinking statistical learning theory: Learning using statistical invariants . Mach. Learn. 108 , 3 (2019), 381 \u2013 423 . Vladimir Vapnik and Rauf Izmailov. 2019. Rethinking statistical learning theory: Learning using statistical invariants. Mach. Learn. 108, 3 (2019), 381\u2013423.","journal-title":"Mach. Learn."},{"key":"e_1_2_1_182_1","doi-asserted-by":"publisher","DOI":"10.1137\/1116025"},{"key":"e_1_2_1_183_1","volume-title":"Proceedings of the Real-Time Image and Video ProcessingConference","volume":"10670","author":"Velasco-Montero Delia","year":"2018","unstructured":"Delia Velasco-Montero , Jorge Fern\u00e1ndez-Berni , Ricardo Carmona-Gal\u00e1n , and Angel Rodr\u00edguez-V\u00e1zquez . 2018 . Performance analysis of real-time DNN inference on raspberry Pi . In Proceedings of the Real-Time Image and Video ProcessingConference , Vol. 10670 . SPIE. Delia Velasco-Montero, Jorge Fern\u00e1ndez-Berni, Ricardo Carmona-Gal\u00e1n, and Angel Rodr\u00edguez-V\u00e1zquez. 2018. Performance analysis of real-time DNN inference on raspberry Pi. In Proceedings of the Real-Time Image and Video ProcessingConference, Vol. 10670. SPIE."},{"key":"e_1_2_1_184_1","volume-title":"Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning.","author":"Venieris Stylianos I.","year":"2018","unstructured":"Stylianos I. Venieris , Alexandros Kouris , and Christos-Savvas Bouganis . 2018 . Deploying deep neural networks in the embedded space . In Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning. Stylianos I. Venieris, Alexandros Kouris, and Christos-Savvas Bouganis. 2018. Deploying deep neural networks in the embedded space. In Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning."},{"key":"e_1_2_1_185_1","volume-title":"et\u00a0al","author":"Wan Alvin","year":"2020","unstructured":"Alvin Wan , Xiaoliang Dai , Peizhao Zhang , Zijian He , Yuandong Tian , Saining Xie , Bichen Wu , Matthew Yu , Tao Xu , Kan Chen , et\u00a0al . 2020 . FBNetV2: Differentiable neural architecture search for spatial and channel dimensions. arXiv:2004.05565. Retrieved from https:\/\/arxiv.org\/abs\/2004.05565. Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, et\u00a0al. 2020. FBNetV2: Differentiable neural architecture search for spatial and channel dimensions. arXiv:2004.05565. Retrieved from https:\/\/arxiv.org\/abs\/2004.05565."},{"key":"e_1_2_1_186_1","volume-title":"HAQ: Hardware-aware automated quantization. arXiv:1811.08886.","author":"Wang Kuan","year":"2018","unstructured":"Kuan Wang , Zhijian Liu , Yujun Lin , Ji Lin , and Song Han . 2018 . HAQ: Hardware-aware automated quantization. arXiv:1811.08886. Retrieved from https:\/\/arxiv.orb\/abs\/1811.08886. Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, and Song Han. 2018. HAQ: Hardware-aware automated quantization. arXiv:1811.08886. Retrieved from https:\/\/arxiv.orb\/abs\/1811.08886."},{"key":"e_1_2_1_187_1","unstructured":"Naigang Wang Jungwook Choi Daniel Brand Chia-Yu Chen and Kailash Gopalakrishnan. 2018. Training deep neural networks with 8-bit floating point numbers. In Advances in Neural Information Processing Systems. 7685\u20137694. Naigang Wang Jungwook Choi Daniel Brand Chia-Yu Chen and Kailash Gopalakrishnan. 2018. Training deep neural networks with 8-bit floating point numbers. In Advances in Neural Information Processing Systems. 7685\u20137694."},{"key":"e_1_2_1_188_1","volume-title":"Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD\u201916)","author":"Wang Wenlin","year":"2016","unstructured":"Wenlin Wang , Changyou Chen , Wenlin Chen , Piyush Rai , and Lawrence Carin . 2016 . Deep distance metric learning with data summarization . In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD\u201916) . Wenlin Wang, Changyou Chen, Wenlin Chen, Piyush Rai, and Lawrence Carin. 2016. Deep distance metric learning with data summarization. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD\u201916)."},{"key":"e_1_2_1_189_1","volume-title":"Convergence of edge computing and deep learning: A comprehensive survey","author":"Wang Xiaofei","year":"2020","unstructured":"Xiaofei Wang , Yiwen Han , Victor C. M. Leung , Dusit Niyato , Xueqiang Yan , and Xu Chen . 2020. Convergence of edge computing and deep learning: A comprehensive survey . IEEE Commun. Surv. Tutor . ( 2020 ). Xiaofei Wang, Yiwen Han, Victor C. M. Leung, Dusit Niyato, Xueqiang Yan, and Xu Chen. 2020. Convergence of edge computing and deep learning: A comprehensive survey. IEEE Commun. Surv. Tutor. (2020)."},{"key":"e_1_2_1_190_1","volume-title":"Skipnet: Learning dynamic routing in convolutional networks. arXiv:1711.09485.","author":"Wang Xin","year":"2017","unstructured":"Xin Wang , Fisher Yu , Zi-Yi Dou , and Joseph E Gonzalez . 2017 . Skipnet: Learning dynamic routing in convolutional networks. arXiv:1711.09485. Retrieved from https:\/\/arxiv.org\/abs\/1711.09485. Xin Wang, Fisher Yu, Zi-Yi Dou, and Joseph E Gonzalez. 2017. Skipnet: Learning dynamic routing in convolutional networks. arXiv:1711.09485. Retrieved from https:\/\/arxiv.org\/abs\/1711.09485."},{"key":"e_1_2_1_191_1","volume-title":"Hoi","author":"Wang Zhihao","year":"2020","unstructured":"Zhihao Wang , Jian Chen , and Steven C. H . Hoi . 2020 . Deep learning for image super-resolution: A survey. IEEE Trans. Pattern Anal. Mach. Intell . (2020). Zhihao Wang, Jian Chen, and Steven C. H. Hoi. 2020. Deep learning for image super-resolution: A survey. IEEE Trans. Pattern Anal. Mach. Intell. (2020)."},{"key":"e_1_2_1_192_1","unstructured":"Jianqiao Wangni Jialei Wang Ji Liu and Tong Zhang. 2018. Gradient sparsification for communication-efficient distributed optimization. In Advances in Neural Information Processing Systems. 1299\u20131309. Jianqiao Wangni Jialei Wang Ji Liu and Tong Zhang. 2018. Gradient sparsification for communication-efficient distributed optimization. In Advances in Neural Information Processing Systems. 1299\u20131309."},{"key":"e_1_2_1_193_1","unstructured":"Wei Wen Chunpeng Wu Yandan Wang Yiran Chen and Hai Li. 2016. Learning structured sparsity in deep neural networks. In Advances in Neural Information Processing Systems. 2074\u20132082. Wei Wen Chunpeng Wu Yandan Wang Yiran Chen and Hai Li. 2016. Learning structured sparsity in deep neural networks. In Advances in Neural Information Processing Systems. 2074\u20132082."},{"key":"e_1_2_1_194_1","volume-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in Neural Information Processing Systems. 1509\u20131519.","author":"Wen Wei","year":"2017","unstructured":"Wei Wen , Cong Xu , Feng Yan , Chunpeng Wu , Yandan Wang , Yiran Chen , and Hai Li . 2017 . Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in Neural Information Processing Systems. 1509\u20131519. Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2017. Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in Neural Information Processing Systems. 1509\u20131519."},{"key":"e_1_2_1_195_1","doi-asserted-by":"crossref","unstructured":"Simon Wiedemann Temesgen Mehari Kevin Kepp and Wojciech Samek. 2020. Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training. arXiv:2004.04729. Retrieved from https:\/\/arxiv.org\/abs\/2004.04729. Simon Wiedemann Temesgen Mehari Kevin Kepp and Wojciech Samek. 2020. Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training. arXiv:2004.04729. Retrieved from https:\/\/arxiv.org\/abs\/2004.04729.","DOI":"10.1109\/CVPRW50498.2020.00368"},{"key":"e_1_2_1_196_1","unstructured":"Martin Wistuba Ambrish Rawat and Tejaswini Pedapati. 2019. A survey on neural architecture search. arXiv:1905.01392. Retrieved from https:\/\/arxiv.org\/abs\/1905.01392. Martin Wistuba Ambrish Rawat and Tejaswini Pedapati. 2019. A survey on neural architecture search. arXiv:1905.01392. Retrieved from https:\/\/arxiv.org\/abs\/1905.01392."},{"key":"e_1_2_1_197_1","unstructured":"Michael M. Wolf. 2018. Mathematical foundations of supervised learning. Michael M. Wolf. 2018. Mathematical foundations of supervised learning."},{"key":"e_1_2_1_198_1","unstructured":"Alexander Wong. 2018. NetScore: Towards universal metrics for large-scale performance analysis of deep neural networks for practical on-device edge usage. Alexander Wong. 2018. NetScore: Towards universal metrics for large-scale performance analysis of deep neural networks for practical on-device edge usage."},{"key":"e_1_2_1_199_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_2_1_200_1","unstructured":"Jiaxiang Wu Weidong Huang Junzhou Huang and Tong Zhang. 2018. Error compensated quantized SGD and its applications to large-scale distributed optimization. arXiv:1806.08054. Retrieved from https:\/\/arxiv.org\/abs\/1806.08054. Jiaxiang Wu Weidong Huang Junzhou Huang and Tong Zhang. 2018. Error compensated quantized SGD and its applications to large-scale distributed optimization. arXiv:1806.08054. Retrieved from https:\/\/arxiv.org\/abs\/1806.08054."},{"key":"e_1_2_1_201_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.125876"},{"key":"e_1_2_1_202_1","volume-title":"Andrew Gordon Wilson, and Christopher De Sa","author":"Yang Guandao","year":"2019","unstructured":"Guandao Yang , Tianyi Zhang , Polina Kirichenko , Junwen Bai , Andrew Gordon Wilson, and Christopher De Sa . 2019 . Swalp : Stochastic weight averaging in low-precision training. arXiv:1904.11943. Retrieved from https:\/\/arxiv.org\/abs\/1904.11943. Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, and Christopher De Sa. 2019. Swalp: Stochastic weight averaging in low-precision training. arXiv:1904.11943. Retrieved from https:\/\/arxiv.org\/abs\/1904.11943."},{"key":"e_1_2_1_203_1","volume-title":"Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Yang Tien-Ju","year":"2017","unstructured":"Tien-Ju Yang , Yu-Hsin Chen , and Vivienne Sze . 2017 . Designing energy-efficient convolutional neural networks using energy-aware pruning . In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917) . IEEE, 6071\u20136079. Tien-Ju Yang, Yu-Hsin Chen, and Vivienne Sze. 2017. Designing energy-efficient convolutional neural networks using energy-aware pruning. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917). IEEE, 6071\u20136079."},{"key":"e_1_2_1_204_1","unstructured":"Tien-Ju Yang Andrew Howard Bo Chen Xiao Zhang Alec Go Mark Sandler Vivienne Sze and Hartwig Adam. 2018. NetAdapt: Platform-Aware neural network adaptation for mobile applications. arxiv:cs.CV\/1804.03230. Retrieved from https:\/\/arxiv.org\/abs\/1804.03230. Tien-Ju Yang Andrew Howard Bo Chen Xiao Zhang Alec Go Mark Sandler Vivienne Sze and Hartwig Adam. 2018. NetAdapt: Platform-Aware neural network adaptation for mobile applications. arxiv:cs.CV\/1804.03230. Retrieved from https:\/\/arxiv.org\/abs\/1804.03230."},{"key":"e_1_2_1_205_1","volume-title":"Proceedings of the International Conference on Machine Learning. 494\u2013503","author":"Yang Wenzhuo","year":"2015","unstructured":"Wenzhuo Yang and Huan Xu . 2015 . Streaming sparse principal component analysis . In Proceedings of the International Conference on Machine Learning. 494\u2013503 . Wenzhuo Yang and Huan Xu. 2015. Streaming sparse principal component analysis. In Proceedings of the International Conference on Machine Learning. 494\u2013503."},{"key":"e_1_2_1_206_1","doi-asserted-by":"crossref","unstructured":"Yukuan Yang Lei Deng Shuang Wu Tianyi Yan Yuan Xie and Guoqi Li. 2020. Training high-performance and large-scale deep neural networks with full 8-bit integers. Neural Netw. (2020). Yukuan Yang Lei Deng Shuang Wu Tianyi Yan Yuan Xie and Guoqi Li. 2020. Training high-performance and large-scale deep neural networks with full 8-bit integers. Neural Netw. (2020).","DOI":"10.1016\/j.neunet.2019.12.027"},{"key":"e_1_2_1_207_1","volume-title":"Proceedings of the 2017 Internet Measurement Conference. ACM, 384\u2013397","author":"Yao Yuanshun","year":"2017","unstructured":"Yuanshun Yao , Zhujun Xiao , Bolun Wang , Bimal Viswanath , Haitao Zheng , and Ben Y Zhao . 2017 . Complexity vs. performance: Empirical analysis of machine learning as a service . In Proceedings of the 2017 Internet Measurement Conference. ACM, 384\u2013397 . Yuanshun Yao, Zhujun Xiao, Bolun Wang, Bimal Viswanath, Haitao Zheng, and Ben Y Zhao. 2017. Complexity vs. performance: Empirical analysis of machine learning as a service. In Proceedings of the 2017 Internet Measurement Conference. ACM, 384\u2013397."},{"key":"e_1_2_1_208_1","doi-asserted-by":"crossref","unstructured":"Heiga Zen Yannis Agiomyrgiannakis Niels Egberts Fergus Henderson and Przemys\u0142aw Szczepaniak. 2016. Fast compact and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices. arXiv:1606.06061. Retrieved from https:\/\/arxiv.org\/abs\/1606.06061. Heiga Zen Yannis Agiomyrgiannakis Niels Egberts Fergus Henderson and Przemys\u0142aw Szczepaniak. 2016. Fast compact and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices. arXiv:1606.06061. Retrieved from https:\/\/arxiv.org\/abs\/1606.06061.","DOI":"10.21437\/Interspeech.2016-522"},{"key":"e_1_2_1_209_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.04.003"},{"key":"e_1_2_1_210_1","unstructured":"Hantian Zhang Jerry Li Kaan Kara Dan Alistarh Ji Liu and Ce Zhang. 2016. The zipml framework for training models with end-to-end low precision: The cans the cannots and a little bit of deep learning. arXiv:1611.05402. Retrieved from https:\/\/arxiv.org\/abs\/1611.05402. Hantian Zhang Jerry Li Kaan Kara Dan Alistarh Ji Liu and Ce Zhang. 2016. The zipml framework for training models with end-to-end low precision: The cans the cannots and a little bit of deep learning. arXiv:1611.05402. Retrieved from https:\/\/arxiv.org\/abs\/1611.05402."},{"key":"e_1_2_1_211_1","volume-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 615\u2013623","author":"Zhang Kai","year":"2017","unstructured":"Kai Zhang , Chuanren Liu , Jie Zhang , Hui Xiong , Eric Xing , and Jieping Ye . 2017 . Randomization or condensation?: Linear-cost matrix sketching via cascaded compression sampling . In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 615\u2013623 . Kai Zhang, Chuanren Liu, Jie Zhang, Hui Xiong, Eric Xing, and Jieping Ye. 2017. Randomization or condensation?: Linear-cost matrix sketching via cascaded compression sampling. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 615\u2013623."},{"key":"e_1_2_1_212_1","volume-title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices. 6848\u20136856.","author":"Zhang Xiangyu","year":"2018","unstructured":"Xiangyu Zhang , Xinyu Zhou , Mengxiao Lin , and Jian Sun . 2018 . Shufflenet: An extremely efficient convolutional neural network for mobile devices. 6848\u20136856. Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun. 2018. Shufflenet: An extremely efficient convolutional neural network for mobile devices. 6848\u20136856."},{"key":"e_1_2_1_213_1","volume-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160.","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou , Yuxin Wu , Zekun Ni , Xinyu Zhou , He Wen , and Yuheng Zou . 2016 . Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160. Retrieved from https:\/\/arxiv.org\/abs\/1606.06160. Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv:1606.06160. Retrieved from https:\/\/arxiv.org\/abs\/1606.06160."},{"key":"e_1_2_1_214_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"e_1_2_1_215_1","volume-title":"TBD: Benchmarking and analyzing deep neural network training. arXiv:1803.06905.","author":"Zhu Hongyu","year":"2018","unstructured":"Hongyu Zhu , Mohamed Akrout , Bojian Zheng , Andrew Pelegris , Amar Phanishayee , Bianca Schroeder , and Gennady Pekhimenko . 2018 . TBD: Benchmarking and analyzing deep neural network training. arXiv:1803.06905. Retrieved from https:\/\/arxiv.org\/abs\/1803.06905. Hongyu Zhu, Mohamed Akrout, Bojian Zheng, Andrew Pelegris, Amar Phanishayee, Bianca Schroeder, and Gennady Pekhimenko. 2018. TBD: Benchmarking and analyzing deep neural network training. arXiv:1803.06905. Retrieved from https:\/\/arxiv.org\/abs\/1803.06905."}],"container-title":["ACM Transactions on Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3450494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T01:40:54Z","timestamp":1672623654000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450494"}},"subtitle":["An Algorithms and Learning Theory Perspective"],"short-title":[],"issued":{"date-parts":[[2021,7,8]]},"references-count":213,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,8,31]]}},"alternative-id":["10.1145\/3450494"],"URL":"https:\/\/doi.org\/10.1145\/3450494","relation":{},"ISSN":["2691-1914","2577-6207"],"issn-type":[{"value":"2691-1914","type":"print"},{"value":"2577-6207","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,8]]},"assertion":[{"value":"2019-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}