{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T17:49:56Z","timestamp":1784224196555,"version":"3.55.0"},"reference-count":94,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T00:00:00Z","timestamp":1649462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2022,7,31]]},"abstract":"<jats:p>\n            <jats:bold>Deep neural network (DNN)<\/jats:bold>\n            models typically have many hyperparameters that can be configured to achieve optimal performance on a particular dataset. Practitioners usually tune the hyperparameters of their DNN models by training a number of trial models with different configurations of the hyperparameters, to find the optimal hyperparameter configuration that maximizes the training accuracy or minimizes the training loss. As such hyperparameter tuning usually focuses on the model accuracy or the loss function, it is not clear and remains under-explored how the process impacts other performance properties of DNN models, such as inference latency and model size. On the other hand, standard DNN models are often large in size and computing-intensive, prohibiting them from being directly deployed in resource-bounded environments such as mobile devices and\n            <jats:bold>Internet of Things (IoT)<\/jats:bold>\n            devices. To tackle this problem, various model optimization techniques (e.g., pruning or quantization) are proposed to make DNN models smaller and less computing-intensive so that they are better suited for resource-bounded environments. However, it is neither clear how the model optimization techniques impact other performance properties of DNN models such as inference latency and battery consumption, nor how the model optimization techniques impact the effect of hyperparameter tuning (i.e., the compounding effect). Therefore, in this paper, we perform a comprehensive study on four representative and widely-adopted DNN models, i.e.,\n            <jats:italic>CNN image classification<\/jats:italic>\n            ,\n            <jats:italic>Resnet-50<\/jats:italic>\n            ,\n            <jats:italic>CNN text classification<\/jats:italic>\n            , and\n            <jats:italic>LSTM sentiment classification<\/jats:italic>\n            , to investigate how different DNN model hyperparameters affect the standard DNN models, as well as how the hyperparameter tuning combined with model optimization affect the optimized DNN models, in terms of various performance properties (e.g., inference latency or battery consumption). Our empirical results indicate that tuning specific hyperparameters has heterogeneous impact on the performance of DNN models across different models and different performance properties. In particular, although the top tuned DNN models usually have very similar accuracy, they may have significantly different performance in terms of other aspects (e.g., inference latency). We also observe that model optimization has a confounding effect on the impact of hyperparameters on DNN model performance. For example, two sets of hyperparameters may result in standard models with similar performance but their performance may become significantly different after they are optimized and deployed on the mobile device. Our findings highlight that practitioners can benefit from paying attention to a variety of performance properties and the confounding effect of model optimization when tuning and optimizing their DNN models.\n          <\/jats:p>","DOI":"10.1145\/3506695","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T17:28:25Z","timestamp":1643650105000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":197,"title":["An Empirical Study of the Impact of Hyperparameter Tuning and Model Optimization on the Performance Properties of Deep Neural Networks"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9920-5855","authenticated-orcid":false,"given":"Lizhi","family":"Liao","sequence":"first","affiliation":[{"name":"Concordia University, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5441-6763","authenticated-orcid":false,"given":"Heng","family":"Li","sequence":"additional","affiliation":[{"name":"Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyi","family":"Shang","sequence":"additional","affiliation":[{"name":"Concordia University, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,4,9]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"https:\/\/towardsdatascience.com\/hyperparameters-in-deep-learning-927f7b2084dd 2019 Hyperparameters in Deep Learning"},{"key":"e_1_3_2_3_2","unstructured":"https:\/\/github.com\/keras-team\/keras-io\/tree\/master\/examples 2020 Keras Code Examples"},{"key":"e_1_3_2_4_2","unstructured":"https:\/\/www.tensorflow.org\/model_optimization\/guide\/pruning\/pruning_with_keras 2020 Pruning in Keras Example"},{"key":"e_1_3_2_5_2","unstructured":"https:\/\/www.tensorflow.org\/model_optimization 2020 Tensorflow Model Optimization"},{"key":"e_1_3_2_6_2","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Yuan Yu et al.2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/. Software available from tensorflow.org."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"e_1_3_2_8_2","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings","author":"Ashok Anubhav","year":"2018","unstructured":"Anubhav Ashok, Nicholas Rhinehart, Fares Beainy, and Kris M. Kitani. 2018. N2N learning: Network to network compression via policy gradient reinforcement learning. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_9_2","article-title":"Building efficient ConvNets using redundant feature pruning","author":"Ayinde Babajide O.","year":"2018","unstructured":"Babajide O. Ayinde and Jacek M. Zurada. 2018. Building efficient ConvNets using redundant feature pruning. arXiv preprint arXiv:1802.07653 (2018).","journal-title":"arXiv preprint arXiv:1802.07653"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICBSLP.2018.8554396"},{"key":"e_1_3_2_11_2","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Workshop Track Proceedings","author":"Baker Bowen","year":"2018","unstructured":"Bowen Baker, Otkrist Gupta, Ramesh Raskar, and Nikhil Naik. 2018. Accelerating neural architecture search using performance prediction. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Workshop Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"e_1_3_2_13_2","series-title":"Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16\u201321 June 2013","first-page":"115","volume":"28","author":"Bergstra James","year":"2013","unstructured":"James Bergstra, Daniel Yamins, and David D. Cox. 2013. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16\u201321 June 2013(JMLR Workshop and Conference Proceedings, Vol. 28). JMLR.org, 115\u2013123."},{"key":"e_1_3_2_14_2","first-page":"2546","volume-title":"Advances in Neural Information Processing Systems","author":"Bergstra James S.","year":"2011","unstructured":"James S. Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. In Advances in Neural Information Processing Systems. 2546\u20132554."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877890"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-4470-8_42"},{"key":"e_1_3_2_17_2","first-page":"3","article-title":"Teoria statistica delle classi e calcolo delle probabilita","volume":"8","author":"Bonferroni Carlo","year":"1936","unstructured":"Carlo Bonferroni. 1936. Teoria statistica delle classi e calcolo delle probabilita. Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commericiali di Firenze 8 (1936), 3\u201362.","journal-title":"Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commericiali di Firenze"},{"key":"e_1_3_2_18_2","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume":"1812","author":"Cai Han","year":"2018","unstructured":"Han Cai, Ligeng Zhu, and Song Han. 2018. ProxylessNAS: Direct neural architecture search on target task and hardware. CoRR abs\/1812.00332 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP.2018.8632592"},{"key":"e_1_3_2_20_2","article-title":"An analysis of deep neural network models for practical applications","author":"Canziani Alfredo","year":"2016","unstructured":"Alfredo Canziani, Adam Paszke, and Eugenio Culurciello. 2016. An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678 (2016).","journal-title":"arXiv preprint arXiv:1605.07678"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950303"},{"key":"e_1_3_2_22_2","article-title":"A survey of model compression and acceleration for deep neural networks","volume":"1710","author":"Cheng Yu","year":"2017","unstructured":"Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. 2017. A survey of model compression and acceleration for deep neural networks. CoRR abs\/1710.09282 (2017).","journal-title":"CoRR"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2975903"},{"key":"e_1_3_2_24_2","article-title":"Keras","author":"Chollet Fran\u00e7ois","year":"2015","unstructured":"Fran\u00e7ois Chollet et\u00a0al. 2015. Keras. https:\/\/keras.io.","journal-title":"https:\/\/keras.io"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315806730"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1590\/S0103-84782013000600003"},{"key":"e_1_3_2_28_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 4171\u20134186."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2011.5949880"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(19)30108-6"},{"key":"e_1_3_2_31_2","series-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10\u201315, 2018","first-page":"1436","volume":"80","author":"Falkner Stefan","year":"2018","unstructured":"Stefan Falkner, Aaron Klein, and Frank Hutter. 2018. BOHB: Robust and efficient hyperparameter optimization at scale. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10\u201315, 2018(Proceedings of Machine Learning Research, Vol. 80), Jennifer G. Dy and Andreas Krause (Eds.). PMLR, 1436\u20131445."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-014-9275-9"},{"key":"e_1_3_2_33_2","article-title":"Auto-Sklearn 2.0","author":"Feurer Matthias","year":"2020","unstructured":"Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, and Frank Hutter. 2020. Auto-Sklearn 2.0. arXiv:2007.04074 [cs.LG] (2020).","journal-title":"arXiv:2007.04074 [cs.LG]"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417050"},{"key":"e_1_3_2_35_2","first-page":"51","article-title":"Variable selection and sensitivity analysis using dynamic trees, with an application to computer code performance tuning","author":"Gramacy Robert B.","year":"2013","unstructured":"Robert B. Gramacy, Matt Taddy, and Stefan M. Wild. 2013. Variable selection and sensitivity analysis using dynamic trees, with an application to computer code performance tuning. The Annals of Applied Statistics (2013), 51\u201380.","journal-title":"The Annals of Applied Statistics"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.58"},{"key":"e_1_3_2_37_2","article-title":"Which Deep Learning Framework is Growing Fastest?","author":"Hale Jeff","year":"2019","unstructured":"Jeff Hale. 2019. Which Deep Learning Framework is Growing Fastest?https:\/\/towardsdatascience.com\/which-deep-learning-framework-is-growing-fastest-3f77f14aa318.","journal-title":"https:\/\/towardsdatascience.com\/which-deep-learning-framework-is-growing-fastest-3f77f14aa318"},{"key":"e_1_3_2_38_2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","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 preprint arXiv:1510.00149 (2015).","journal-title":"arXiv preprint arXiv:1510.00149"},{"key":"e_1_3_2_39_2","article-title":"Learning both weights and connections for efficient neural networks","volume":"1506","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William J. Dally. 2015. Learning both weights and connections for efficient neural networks. CoRR abs\/1506.02626 (2015).","journal-title":"CoRR"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISOCC.2017.8368904"},{"key":"e_1_3_2_41_2","article-title":"Soft filter pruning for accelerating deep convolutional neural networks","author":"He Yang","year":"2018","unstructured":"Yang He, Guoliang Kang, Xuanyi Dong, Yanwei Fu, and Yi Yang. 2018. Soft filter pruning for accelerating deep convolutional neural networks. arXiv preprint arXiv:1808.06866 (2018).","journal-title":"arXiv preprint arXiv:1808.06866"},{"key":"e_1_3_2_42_2","article-title":"MONAS: Multi-objective neural architecture search using reinforcement learning","volume":"1806","author":"Hsu Chi-Hung","year":"2018","unstructured":"Chi-Hung Hsu, Shu-Huan Chang, Da-Cheng Juan, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, and Shih-Chieh Chang. 2018. MONAS: Multi-objective neural architecture search using reinforcement learning. CoRR abs\/1806.10332 (2018).","journal-title":"CoRR"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-44973-4_40"},{"key":"e_1_3_2_44_2","series-title":"Proceedings of the 31st International Conference on Machine Learning, ICML 2014, Beijing, China, 21\u201326 June 2014","first-page":"754","volume":"32","author":"Hutter Frank","year":"2014","unstructured":"Frank Hutter, Holger H. Hoos, and Kevin Leyton-Brown. 2014. An efficient approach for assessing hyperparameter importance. In Proceedings of the 31st International Conference on Machine Learning, ICML 2014, Beijing, China, 21\u201326 June 2014(JMLR Workshop and Conference Proceedings, Vol. 32). JMLR.org, 754\u2013762."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.005"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330648"},{"key":"e_1_3_2_47_2","article-title":"Hands on Hyperparameter Tuning with Keras Tuner","author":"Prost Julie","year":"2020","unstructured":"Julie Prost. 2020. Hands on Hyperparameter Tuning with Keras Tuner. https:\/\/www.sicara.ai\/blog\/hyperparameter-tuning-keras-tuner.","journal-title":"https:\/\/www.sicara.ai\/blog\/hyperparameter-tuning-keras-tuner"},{"key":"e_1_3_2_48_2","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","author":"Kim Yong-Deok","year":"2015","unstructured":"Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, and Dongjun Shin. 2015. Compression of deep convolutional neural networks for fast and low power mobile applications. arXiv preprint arXiv:1511.06530 (2015).","journal-title":"arXiv preprint arXiv:1511.06530"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2005.851274"},{"key":"e_1_3_2_50_2","first-page":"25:1\u201325:5","article-title":"Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA","volume":"18","author":"Kotthoff Lars","year":"2017","unstructured":"Lars Kotthoff, Chris Thornton, Holger H. Hoos, Frank Hutter, and Kevin Leyton-Brown. 2017. Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA. J. Mach. Learn. Res. 18 (2017), 25:1\u201325:5.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_51_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_53_2","article-title":"MNIST handwritten digit database","volume":"2","author":"LeCun Yann","year":"2010","unstructured":"Yann LeCun, Corinna Cortes, and CJ Burges. 2010. MNIST handwritten digit database. ATT Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist 2 (2010).","journal-title":"ATT Labs [Online]."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.76"},{"key":"e_1_3_2_55_2","article-title":"Pruning filters for efficient ConvNets","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient ConvNets. arXiv preprint arXiv:1608.08710 (2016).","journal-title":"arXiv preprint arXiv:1608.08710"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09866-z"},{"key":"e_1_3_2_57_2","article-title":"Best practices for scientific research on neural architecture search","volume":"1909","author":"Lindauer Marius","year":"2019","unstructured":"Marius Lindauer and Frank Hutter. 2019. Best practices for scientific research on neural architecture search. CoRR abs\/1909.02453 (2019).","journal-title":"CoRR"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2695223"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2020.102989"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICA.2019.8873454"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016120"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_63_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Mehrotra Abhinav","year":"2021","unstructured":"Abhinav Mehrotra, Alberto Gil C. P. Ramos, Sourav Bhattacharya, Lukasz Dudziak, Ravichander Vipperla, Thomas C. P. Chau, Mohamed S. Abdelfattah, Samin Ishtiaq, and Nicholas Donald Lane. 2021. NAS-Bench-ASR: Reproducible neural architecture search for speech recognition. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. OpenReview.net."},{"key":"e_1_3_2_64_2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013).","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"e_1_3_2_65_2","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov Pavlo","year":"2016","unstructured":"Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016).","journal-title":"arXiv preprint arXiv:1611.06440"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.20982\/tqmp.04.1.p013"},{"key":"e_1_3_2_67_2","article-title":"Keras Tuner","author":"O\u2019Malley Tom","year":"2019","unstructured":"Tom O\u2019Malley, Elie Bursztein, James Long, Fran\u00e7ois Chollet, Haifeng Jin, Luca Invernizzi, et\u00a0al. 2019. Keras Tuner. https:\/\/github.com\/keras-team\/keras-tuner.","journal-title":"https:\/\/github.com\/keras-team\/keras-tuner"},{"key":"e_1_3_2_68_2","series-title":"Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2019, Tel Aviv, Israel, July 22\u201325, 2019","first-page":"766","volume":"115","author":"Paria Biswajit","year":"2019","unstructured":"Biswajit Paria, Kirthevasan Kandasamy, and Barnab\u00e1s P\u00f3czos. 2019. A flexible framework for multi-objective Bayesian optimization using random scalarizations. In Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2019, Tel Aviv, Israel, July 22\u201325, 2019(Proceedings of Machine Learning Research, Vol. 115), Amir Globerson and Ricardo Silva (Eds.). AUAI Press, 766\u2013776."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIS49240.2020.9257657"},{"key":"e_1_3_2_71_2","series-title":"Communications in Computer and Information Science","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-981-15-1398-5_1","volume-title":"Human Brain and Artificial Intelligence - First International Workshop, HBAI 2019, Held in Conjunction with IJCAI 2019, Macao, China, August 12, 2019, Revised Selected Papers","author":"Rapaport Elad","year":"2019","unstructured":"Elad Rapaport, Oren Shriki, and Rami Puzis. 2019. EEGNAS: Neural architecture search for electroencephalography data analysis and decoding. In Human Brain and Artificial Intelligence - First International Workshop, HBAI 2019, Held in Conjunction with IJCAI 2019, Macao, China, August 12, 2019, Revised Selected Papers(Communications in Computer and Information Science, Vol. 1072), An Zeng, Dan Pan, Tianyong Hao, Daoqiang Zhang, Yiyu Shi, and Xiaowei Song (Eds.). Springer, 3\u201320."},{"key":"e_1_3_2_72_2","article-title":"Optimal hyperparameters for deep LSTM-networks for sequence labeling tasks","author":"Reimers Nils","year":"2017","unstructured":"Nils Reimers and Iryna Gurevych. 2017. Optimal hyperparameters for deep LSTM-networks for sequence labeling tasks. arXiv preprint arXiv:1707.06799 (2017).","journal-title":"arXiv preprint arXiv:1707.06799"},{"key":"e_1_3_2_73_2","article-title":"A comprehensive survey of neural architecture search: Challenges and solutions","volume":"2006","author":"Ren Pengzhen","year":"2020","unstructured":"Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Xiaojiang Chen, and Xin Wang. 2020. A comprehensive survey of neural architecture search: Challenges and solutions. CoRR abs\/2006.02903 (2020).","journal-title":"CoRR"},{"issue":"3","key":"e_1_3_2_74_2","first-page":"2701","article-title":"A study on normalization techniques for privacy preserving data mining","volume":"5","author":"Saranya C.","year":"2013","unstructured":"C. Saranya and G. Manikandan. 2013. A study on normalization techniques for privacy preserving data mining. International Journal of Engineering and Technology (IJET) 5, 3 (2013), 2701\u20132704.","journal-title":"International Journal of Engineering and Technology (IJET)"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1519\/JSC.0000000000001221"},{"key":"e_1_3_2_76_2","first-page":"2951","volume-title":"Advances in Neural Information Processing Systems","author":"Snoek Jasper","year":"2012","unstructured":"Jasper Snoek, Hugo Larochelle, and Ryan P. Adams. 2012. Practical Bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems. 2951\u20132959."},{"issue":"56","key":"e_1_3_2_77_2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15, 56 (2014), 1929\u20131958.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1002\/9780470183410"},{"key":"e_1_3_2_79_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Stock Pierre","year":"2021","unstructured":"Pierre Stock, Angela Fan, Benjamin Graham, Edouard Grave, R\u00e9mi Gribonval, Herv\u00e9 J\u00e9gou, and Armand Joulin. 2021. Training with quantization noise for extreme model compression. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021."},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2018.04.012"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/KSE.2017.8119458"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1058"},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0000000000001027"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274840"},{"key":"e_1_3_2_89_2","series-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event","first-page":"11875","volume":"139","author":"Yao Zhewei","year":"2021","unstructured":"Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, and Kurt Keutzer. 2021. HAWQ-V3: Dyadic neural network quantization. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event(Proceedings of Machine Learning Research, Vol. 139). PMLR, 11875\u201311886."},{"key":"e_1_3_2_90_2","article-title":"Progressive DNN compression: A key to achieve ultra-high weight pruning and quantization rates using ADMM","author":"Ye Shaokai","year":"2019","unstructured":"Shaokai Ye, Xiaoyu Feng, Tianyun Zhang, Xiaolong Ma, Sheng Lin, Zhengang Li, Kaidi Xu, Wujie Wen, Sijia Liu, Jian Tang, et\u00a0al. 2019. Progressive DNN compression: A key to achieve ultra-high weight pruning and quantization rates using ADMM. arXiv preprint arXiv:1903.09769 (2019).","journal-title":"arXiv preprint arXiv:1903.09769"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88910-6"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/IICAIET49801.2020.9257825"},{"key":"e_1_3_2_93_2","unstructured":"Julie Zelenski K. Huffman K. Schwarz and Marty Stepp. 2012. Huffman encoding and data compression."},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2007.892759"},{"key":"e_1_3_2_95_2","series-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event","first-page":"11096","volume":"119","author":"Zhang Richard","year":"2020","unstructured":"Richard Zhang and Daniel Golovin. 2020. Random hypervolume scalarizations for provable multi-objective black box optimization. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event(Proceedings of Machine Learning Research, Vol. 119). PMLR, 11096\u201311105."}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3506695","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3506695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:50Z","timestamp":1750191110000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3506695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,9]]},"references-count":94,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,7,31]]}},"alternative-id":["10.1145\/3506695"],"URL":"https:\/\/doi.org\/10.1145\/3506695","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,9]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}