{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:42:20Z","timestamp":1773376940017,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1641\/21"],"award-info":[{"award-number":["1641\/21"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2131115"],"award-info":[{"award-number":["CCF-2131115"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/isit63088.2025.11195544","type":"proceedings-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:48:08Z","timestamp":1760982488000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Optimal Quantization for Matrix Multiplication"],"prefix":"10.1109","author":[{"given":"Or","family":"Ordentlich","sequence":"first","affiliation":[{"name":"Hebrew University of Jerusalem,Computer Science and Engineering,Jerusalem,Israel"}]},{"given":"Yury","family":"Polyanskiy","sequence":"additional","affiliation":[{"name":"MIT,Dept. EECS,Cambridge,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/isit63088.2025.11195544"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02165411"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS57990.2023.00130"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977912.134"},{"key":"ref6","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/2200000035"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492920000021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539704442684"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2493252.2493254"},{"key":"ref13","article-title":"Dynamic network surgery for efficient dnns","volume":"29","author":"Guo","year":"2016","journal-title":"Advances in neural information processing systems"},{"issue":"187","key":"ref14","first-page":"1","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref17","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"27168","article-title":"Zeroquant: Efficient and affordable post-training quantization for largescale transformers","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao","year":"2023"},{"key":"ref20","article-title":"The era of 1-bit llms: All large language models are in 1.58 bits","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Quip#: Even better 1 lm quantization with hadamard incoherence and lattice codebooks","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Qtip: Quantization with trellises and incoherence processing","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Quarot: Outlier-free 4-bit inference in rotated llms","author":"Ashkboos","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Frantar","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT57864.2024.10619604"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2032853"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2090225"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2402972"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2014.37"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2963864"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1983.1056761"},{"key":"ref32","article-title":"NestQuant: Nested lattice quantization for matrix products and LLMs","author":"Savkin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT63088.2025.11195282"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/9781108966351"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.834787"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139045520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2571719"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1090\/jams\/984"}],"event":{"name":"2025 IEEE International Symposium on Information Theory (ISIT)","location":"Ann Arbor, MI, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,27]]}},"container-title":["2025 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11195206\/11195207\/11195544.pdf?arnumber=11195544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:29:28Z","timestamp":1773347368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/isit63088.2025.11195544","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}