{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:50:25Z","timestamp":1763751025722,"version":"3.45.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of Hong Kong, SAR","award":["CUHK14208021"],"award-info":[{"award-number":["CUHK14208021"]}]},{"name":"MIND Project","award":["MINDXZ202404"],"award-info":[{"award-number":["MINDXZ202404"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcad.2024.3476450","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T13:48:49Z","timestamp":1728481729000},"page":"1394-1405","source":"Crossref","is-referenced-by-count":1,"title":["BAQE: Backend-Adaptive DNN Deployment via Synchronous Bayesian Quantization and Hardware Configuration Exploration"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9501-9254","authenticated-orcid":false,"given":"Wenqian","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"given":"Shuo","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1742-0090","authenticated-orcid":false,"given":"Chen","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8179-0996","authenticated-orcid":false,"given":"Zixiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4810","authenticated-orcid":false,"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16950"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00801"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00916"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.676564"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_16"},{"key":"ref11","first-page":"11875","article-title":"HAWQ-V3: Dyadic neural network quantization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref15","first-page":"1","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3241110"},{"key":"ref18","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nagel"},{"key":"ref19","first-page":"1","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3300309"},{"key":"ref21","article-title":"Mixed precision quantization of ConvNets via differentiable neural architecture search","author":"Wu","year":"2018","journal-title":"arXiv:1812.00090"},{"key":"ref22","first-page":"579","article-title":"TVM: AN automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref23","first-page":"3393","article-title":"Learning to optimize tensor programs","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"31","author":"Chen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218700"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3317169"},{"key":"ref26","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Zheng"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.250"},{"key":"ref28","first-page":"1","article-title":"Multi-task Gaussian process prediction","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"20","author":"Bonilla"},{"key":"ref29","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref31","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv:1805.06085"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/10934961\/10711872.pdf?arnumber=10711872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:43:10Z","timestamp":1763750590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10711872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":31,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3476450","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}