{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:54:43Z","timestamp":1781866483697,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3797248.3815401","type":"proceedings-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:46:08Z","timestamp":1781865968000},"page":"14-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hyperparameter Auto-tuning for Sustainable LLM Fine-tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7867-6603","authenticated-orcid":false,"given":"Dayuan","family":"Chen","sequence":"first","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2693-7419","authenticated-orcid":false,"given":"Ziliang","family":"Zong","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/IGCC.2015.7393699"},{"key":"e_1_3_3_2_3_2","first-page":"11","volume-title":"2024 2nd International Conference on Disruptive Technologies (ICDT)","author":"Agrawal Parul","year":"2024","unstructured":"Parul Agrawal et\u00a0al. 2024. A survey on hyperparameter optimization of machine learning models. In 2024 2nd International Conference on Disruptive Technologies (ICDT). IEEE, 11\u201315."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Bernd Bischl Martin Binder Michel Lang Tobias Pielok Jakob Richter Stefan Coors Janek Thomas Theresa Ullmann Marc Becker Anne-Laure Boulesteix et\u00a0al. 2023. Hyperparameter optimization: Foundations algorithms best practices and open challenges. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 13 2 (2023) e1484.","DOI":"10.1002\/widm.1484"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW63119.2024.00162"},{"key":"e_1_3_3_2_6_2","unstructured":"Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1604.06174 (2016)."},{"key":"e_1_3_3_2_7_2","unstructured":"Wei-Lin Chiang Lianmin Zheng Ying Sheng Anastasios\u00a0Nikolas Angelopoulos Tianle Li Dacheng Li Hao Zhang Banghua Zhu Michael Jordan Joseph\u00a0E. Gonzalez and Ion Stoica. 2024. Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference. arxiv:https:\/\/arXiv.org\/abs\/2403.04132\u00a0[cs.AI]"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Aaron Clauset Cosma\u00a0Rohilla Shalizi and Mark\u00a0EJ Newman. 2009. Power-law distributions in empirical data. SIAM review 51 4 (2009) 661\u2013703.","DOI":"10.1137\/070710111"},{"key":"e_1_3_3_2_9_2","volume-title":"North American Chapter of the Association for Computational Linguistics","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 North American Chapter of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:52967399"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC59175.2023.10253886"},{"key":"e_1_3_3_2_11_2","unstructured":"Abraham\u00a0J Fetterman Ellie Kitanidis Joshua Albrecht Zachary Polizzi Bryden Fogelman Maksis Knutins Bartosz Wr\u00f3blewski James\u00a0B Simon and Kanjun Qiu. 2023. Tune as you scale: Hyperparameter optimization for compute efficient training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.08055 (2023)."},{"key":"e_1_3_3_2_12_2","unstructured":"Peter\u00a0I Frazier. 2018. A tutorial on Bayesian optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1807.02811 (2018)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717480"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"e_1_3_3_2_15_2","unstructured":"Leona Hennig Tanja Tornede and Marius Lindauer. 2024. Towards leveraging automl for sustainable deep learning: A multi-objective hpo approach on deep shift neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.01965 (2024)."},{"key":"e_1_3_3_2_16_2","unstructured":"Kai Huang Hanyun Yin Heng Huang and Wei Gao. 2023. Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.13192 (2023)."},{"key":"e_1_3_3_2_17_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2001.08361 (2020)."},{"key":"e_1_3_3_2_18_2","volume-title":"Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC \u201920)","author":"Keahey Kate","year":"2020","unstructured":"Kate Keahey, Jason Anderson, Zhuo Zhen, Pierre Riteau, Paul Ruth, Dan Stanzione, Mert Cevik, Jacob Colleran, Haryadi\u00a0S. Gunawi, Cody Hammock, Joe Mambretti, Alexander Barnes, Fran\u00e7ois Halbach, Alex Rocha, and Joe Stubbs. 2020. Lessons Learned from the Chameleon Testbed. In Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC \u201920). USENIX Association."},{"key":"e_1_3_3_2_19_2","unstructured":"Lisha Li Kevin Jamieson Giulia DeSalvo Afshin Rostamizadeh and Ameet Talwalkar. 2018. Hyperband: A novel bandit-based approach to hyperparameter optimization. Journal of Machine Learning Research 18 185 (2018) 1\u201352."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17031"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Yiheng Liu Tianle Han Siyuan Ma Jiayue Zhang Yuanyuan Yang Jiaming Tian Hao He Antong Li Mengshen He Zhengliang Liu et\u00a0al. 2023. Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiology (2023) 100017.","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"e_1_3_3_2_22_2","unstructured":"S Patro. 2015. Normalization: A preprocessing stage. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1503.06462 (2015)."},{"key":"e_1_3_3_2_23_2","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding with unsupervised learning. OpenAI Res (2018)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363447"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198821939.001.0001"},{"key":"e_1_3_3_2_28_2","first-page":"3","volume-title":"NeurIPS 2020 competition and demonstration track","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 NeurIPS 2020 competition and demonstration track. PMLR, 3\u201326."},{"key":"e_1_3_3_2_29_2","unstructured":"Jonghyeon Won Hyun-Suk Lee and Jang-Won Lee. 2025. A review on multi-fidelity hyperparameter optimization in machine learning. ICT Express (2025)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.394"},{"key":"e_1_3_3_2_31_2","unstructured":"Zhewei Yao Reza\u00a0Yazdani Aminabadi Olatunji Ruwase Samyam Rajbhandari Xiaoxia Wu Ammar\u00a0Ahmad Awan Jeff Rasley Minjia Zhang Conglong Li Connor Holmes et\u00a0al. 2023. Deepspeed-chat: Easy fast and affordable rlhf training of chatgpt-like models at all scales. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.01320 (2023)."},{"key":"e_1_3_3_2_32_2","first-page":"119","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"You Jie","year":"2023","unstructured":"Jie You, Jae-Won Chung, and Mosharaf Chowdhury. 2023. Zeus: Understanding and optimizing GPU energy consumption of DNN training. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 119\u2013139."},{"key":"e_1_3_3_2_33_2","unstructured":"Minjia Zhang and Yuxiong He. 2020. Accelerating training of transformer-based language models with progressive layer dropping. Advances in neural information processing systems 33 (2020) 14011\u201314023."},{"key":"e_1_3_3_2_34_2","unstructured":"Yang Zhang Haiyang Wu and Yuekui Yang. 2024. FlexHB: a More Efficient and Flexible Framework for Hyperparameter Optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.13641 (2024)."}],"event":{"name":"IGSC '26: International Green and Sustainable Computing Conference","location":"Canandaigua USA","acronym":"IGSC 2026","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 16th ACM International Green and Sustainable Computing Conference"],"original-title":[],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:48:59Z","timestamp":1781866139000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797248.3815401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":33,"alternative-id":["10.1145\/3797248.3815401","10.1145\/3797248"],"URL":"https:\/\/doi.org\/10.1145\/3797248.3815401","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}