{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:28:36Z","timestamp":1783096116349,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3716368.3735291","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:58:23Z","timestamp":1751032703000},"page":"854-859","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Energy-Efficient Quantization-Aware Training with Dynamic Bit-Width Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6075-0880","authenticated-orcid":false,"given":"Ali","family":"Karkehabadi","sequence":"first","affiliation":[{"name":"University of California, Davis, DAVIS, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4052-8075","authenticated-orcid":false,"given":"Avesta","family":"Sasan","sequence":"additional","affiliation":[{"name":"University of California, Davis, DAVIS, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"5145","volume-title":"Advances in Neural Information Processing Systems","author":"Banner Ron","year":"2018","unstructured":"Ron Banner, Itay Hubara, Elad Hoffer, and Daniel Soudry. 2018. Scalable Methods for 8-bit Training of Neural Networks. In Advances in Neural Information Processing Systems. 5145\u20135153."},{"key":"e_1_3_3_1_3_2","unstructured":"Jungwook Choi Zhuo Wang Swagath Venkataramani Pierce I-Jen Chuang Vijayalakshmi Srinivasan and Kailash Gopalakrishnan. 2018. Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1805.06085 (2018)."},{"key":"e_1_3_3_1_4_2","first-page":"1","volume-title":"IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","author":"Gong Chunlei","year":"2020","unstructured":"Chunlei Gong, Zhihui Jiang, Wenrui Wang, Qizhao Liu, Zhenfei Wu, Yi Ren, Qinghua Yao, Menglin Dong, Ming Lin, and Bo Zhao. 2020. Mixed Precision Neural Architecture Search for Energy Efficient Deep Learning. In IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1\u20139."},{"key":"e_1_3_3_1_5_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William\u00a0J Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_7_2","unstructured":"Xijie Huang Zechun Liu Shih-Yang Liu and Kwang-Ting Cheng. [n. d.]. Robust and Efficient Quantization-aware Training via Coreset Selection. Transactions on Machine Learning Research ([n. d.])."},{"key":"e_1_3_3_1_8_2","unstructured":"Xijie Huang Zechun Liu Shih-Yang Liu and Kwang-Ting Cheng. 2023. Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.07215 (2023)."},{"key":"e_1_3_3_1_9_2","unstructured":"Xijie Huang Zechun Liu Shih-Yang Liu and Kwang-Ting Cheng. 2024. Robust and Efficient Quantization-aware Training via Coreset Selection. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_3_1_10_2","unstructured":"Itay Hubara Matthieu Courbariaux Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2017. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. Journal of Machine Learning Research 18 187 (2017) 1\u201330."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3660391"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCAS61159.2024.10539909"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST63249.2024.10805345"},{"key":"e_1_3_3_1_15_2","unstructured":"Raghuraman Krishnamoorthi. 2018. Quantizing Deep Convolutional Networks for Efficient Inference: A Whitepaper. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.08342 (2018)."},{"key":"e_1_3_3_1_16_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. Technical report University of Toronto 1 4 (2009) 7."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun L\u00e9on Bottou Yoshua Bengio and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86 11 (1998) 2278\u20132324.","DOI":"10.1109\/5.726791"},{"key":"e_1_3_3_1_18_2","first-page":"7197","volume-title":"International Conference on Machine Learning","author":"Nagel Markus","year":"2019","unstructured":"Markus Nagel, Rana\u00a0Ali Amjad, Mart\u00a0van Baalen, Christos Louizos, and Tijmen Blankevoort. 2019. Up or Down? Adaptive Rounding for Post-Training Quantization. In International Conference on Machine Learning. 7197\u20137206."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Yury Nahshan Brian Chmiel Chaim Baskin Evgenii Zheltonozhskii Ron Banner Alex\u00a0M Bronstein and Avi Mendelson. 2021. Loss Aware Post-training Quantization. Machine Learning 110 11 (2021) 3245\u20133262.","DOI":"10.1007\/s10994-021-06053-z"},{"key":"e_1_3_3_1_21_2","unstructured":"Tsui-Wei Weng Zhangyang Duan Erfan Zangeneh Alaa Khaddaj Zirui Wang Baris Kasikci Suren Jayasuriya and Gu-Yeon Wei. 2023. A Survey on Efficient Neural Networks: Compression Acceleration and Edge Intelligence. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Tien-Ju Yang Yu-Hsin Chen and Vivienne Sze. 2017. Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017) 5687\u20135695.","DOI":"10.1109\/CVPR.2017.643"}],"event":{"name":"GLSVLSI '25: Great Lakes Symposium on VLSI 2025","location":"New Orleans LA USA","acronym":"GLSVLSI '25","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2025"],"original-title":[],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:38:40Z","timestamp":1751035120000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716368.3735291"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":21,"alternative-id":["10.1145\/3716368.3735291","10.1145\/3716368"],"URL":"https:\/\/doi.org\/10.1145\/3716368.3735291","relation":{},"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"2025-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}