{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:14Z","timestamp":1750309334384,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB1715200"],"award-info":[{"award-number":["2021YFB1715200"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671933","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"2340-2351","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4324-6989","authenticated-orcid":false,"given":"Zhongyi","family":"Pei","sequence":"first","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8836-6773","authenticated-orcid":false,"given":"Zhiyao","family":"Cen","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6820-5427","authenticated-orcid":false,"given":"Yipeng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1698-8992","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, EIRI, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3704-2322","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5412-9120","authenticated-orcid":false,"given":"Mingsheng","family":"Long","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6841-7943","authenticated-orcid":false,"given":"Jianmin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2023. Neural Network Intelligence. https:\/\/github.com\/microsoft\/nni"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--1--4842--6579--6"},{"key":"e_1_3_2_2_3_1","volume-title":"Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24","author":"Bergstra James","year":"2011","unstructured":"James Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_2_2_4_1","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra James","year":"2012","unstructured":"James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of machine learning research 13, 2 (2012).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS.2019.00059"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510099"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981072"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981072"},{"key":"e_1_3_2_2_10_1","volume-title":"Jost Tobias Springenberg, and Frank Hutter","author":"Domhan Tobias","year":"2015","unstructured":"Tobias Domhan, Jost Tobias Springenberg, and Frank Hutter. 2015. Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves. In Twenty-fourth international joint conference on artificial intelligence."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Katharina Eggensperger Philipp M\u00fcller Neeratyoy Mallik Matthias Feurer Ren\u00e9 Sass Aaron Klein Noor Awad Marius Lindauer and Frank Hutter. 2022. HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO. https:\/\/doi.org\/10.48550\/arXiv.2109.06716 arXiv:2109.06716 [cs].","DOI":"10.48550\/arXiv.2109.06716"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--16722--6_10"},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR, 1437--1446","author":"Falkner Stefan","year":"2018","unstructured":"Stefan Falkner, Aaron Klein, and Frank Hutter. 2018. BOHB: Robust and efficient hyperparameter optimization at scale. In International Conference on Machine Learning. PMLR, 1437--1446."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-05318--5_1"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"e_1_3_2_2_16_1","first-page":"2011","article-title":"Sequential model-based optimization for general algorithm configuration. In Learning and Intelligent Optimization: 5th International Conference","volume":"21","author":"Hutter Frank","year":"2011","unstructured":"Frank Hutter, Holger H Hoos, and Kevin Leyton-Brown. 2011. Sequential model-based optimization for general algorithm configuration. In Learning and Intelligent Optimization: 5th International Conference, LION 5, Rome, Italy, January 17--21, 2011. Selected Papers 5. Springer, 507--523.","journal-title":"LION 5, Rome, Italy"},{"key":"e_1_3_2_2_17_1","volume-title":"International Conference on Machine Learning. PMLR, 3519--3529","author":"Kornblith Simon","year":"2019","unstructured":"Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In International Conference on Machine Learning. PMLR, 3519--3529."},{"key":"e_1_3_2_2_18_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"e_1_3_2_2_20_1","first-page":"1","article-title":"Hyperband: a novel bandit-based approach to hyperparameter optimization","volume":"18","author":"Li Lisha","year":"2017","unstructured":"Lisha Li, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, and Ameet Talwalkar. 2017. Hyperband: a novel bandit-based approach to hyperparameter optimization. The Journal of Machine Learning Research 18, 1 (Jan. 2017), 6765--6816.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_2_21_1","volume-title":"Reliability assurance for deep neural network architectures against numerical defects. arXiv preprint arXiv:2302.06086","author":"Li Linyi","year":"2023","unstructured":"Linyi Li, Yuhao Zhang, Luyao Ren, Yingfei Xiong, and Tao Xie. 2023. Reliability assurance for deep neural network architectures against numerical defects. arXiv preprint arXiv:2302.06086 (2023)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236082"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of Machine Learning and Systems 3 (March","author":"Rauschmayr Nathalie","year":"2021","unstructured":"Nathalie Rauschmayr, Vikas Kumar, Rahul Huilgol, Andrea Olgiati, Satadal Bhattacharjee, Nihal Harish, Vandana Kannan, Amol Lele, Anirudh Acharya, Jared Nielsen, Lakshmi Ramakrishnan, Ishan Bhatt, Kohen Chia, Neelesh Dodda, Zhihan Li, Jiacheng Gu, Miyoung Choi, Balajee Nagarajan, Jeffrey Geevarghese, Denis Davydenko, Sifei Li, Lu Huang, Edward Kim, Tyler Hill, and Krishnaram Kenthapadi. 2021. Amazon SageMaker Debugger: A System for Real-Time Insights into Machine Learning Model Training. Proceedings of Machine Learning and Systems 3 (March 2021), 770--782."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Hasim Sak Andrew W Senior and Fran\u00e7oise Beaufays. 2014. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. (2014).","DOI":"10.21437\/Interspeech.2014-80"},{"key":"e_1_3_2_2_26_1","first-page":"20825","article-title":"Cockpit: A practical debugging tool for the training of deep neural networks","volume":"34","author":"Schneider Frank","year":"2021","unstructured":"Frank Schneider, Felix Dangel, and Philipp Hennig. 2021. Cockpit: A practical debugging tool for the training of deep neural networks. Advances in Neural Information Processing Systems 34 (2021), 20825--20837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3334480.3382879"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445538"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_3_2_2_30_1","volume-title":"Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems 25","author":"Snoek Jasper","year":"2012","unstructured":"Jasper Snoek, Hugo Larochelle, and Ryan P Adams. 2012. Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems 25 (2012)."},{"volume-title":"Diagnosing convolutional neural networks using their spectral response. In 2018 Digital Image Computing: Techniques and Applications (DICTA)","author":"Stamatescu Victor","key":"e_1_3_2_2_31_1","unstructured":"Victor Stamatescu and Mark D McDonnell. 2018. Diagnosing convolutional neural networks using their spectral response. In 2018 Digital Image Computing: Techniques and Applications (DICTA). IEEE, 1--8."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the NeurIPS 2020 Competition and Demonstration Track. PMLR, 3--26","author":"Turner Ryan","year":"2021","unstructured":"Ryan Turner, David Eriksson, Michael McCourt, Juha Kiili, Eero Laaksonen, Zhen Xu, and Isabelle Guyon. 2021. Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020. In Proceedings of the NeurIPS 2020 Competition and Demonstration Track. PMLR, 3--26. ISSN: 2640--3498."},{"key":"e_1_3_2_2_34_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510071"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00034"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of The 35th Uncertainty in Artificial Intelligence Conference. PMLR, 788--798","author":"Wu Jian","year":"2020","unstructured":"Jian Wu, Saul Toscano-Palmerin, Peter I. Frazier, and Andrew Gordon Wilson. 2020. Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning. In Proceedings of The 35th Uncertainty in Artificial Intelligence Conference. PMLR, 788--798. ISSN: 2640--3498."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/800"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Haoyi Xiong Haozhe An Xuhong Li Xingjian Li Zhanxing Zhu Yingying Ma and Zeyi Sun. 2023. Model Selection for Deep Learning with Gradient Norms: An Empirical Study. (2023).","DOI":"10.21203\/rs.3.rs-2408527\/v1"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.061"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00043"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409720"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Barcelona Spain","acronym":"KDD '24"},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671933","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:15Z","timestamp":1750291455000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671933"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":42,"alternative-id":["10.1145\/3637528.3671933","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671933","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}