{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T08:18:14Z","timestamp":1725783494190},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,19]]},"DOI":"10.1109\/iscas58744.2024.10558050","type":"proceedings-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:22:52Z","timestamp":1719940972000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Neural Compression with Inference-time Decoding"],"prefix":"10.1109","author":[{"given":"Clement","family":"Metz","sequence":"first","affiliation":[{"name":"CEA List, Universit&#x00E9; Paris-Saclay,Palaiseau,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Bichler","sequence":"additional","affiliation":[{"name":"CEA List,Palaiseau,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Dupret","sequence":"additional","affiliation":[{"name":"CEA Leti,Palaiseau,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"What is the state of neural network pruning?","author":"Blalock","year":"2020","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/iccv.2019.00038"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICCV.2019.00038"},{"year":"2014","author":"Duda","journal-title":"Asymmetric numeral systems: entropy coding combining speed of huffman coding with compression rate of arithmetic coding","key":"ref4"},{"year":"2020","author":"Esser","journal-title":"Learned step size quantization","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-030-58574-7_27"},{"year":"2016","author":"Han","article-title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/JRPROC.1952.273898"},{"year":"2019","author":"Jin","journal-title":"Towards efficient training for neural network quantization","key":"ref10"},{"year":"2018","author":"Krishnamoorthi","journal-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","key":"ref11"},{"year":"2009","author":"Krizhevsky","journal-title":"Learning multiple layers of features from tiny images","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1147\/rd.282.0135"},{"key":"ref14","article-title":"Additive powers-of-two quantization: A non-uniform discretization for neural networks","author":"Li","year":"2019","journal-title":"CoRR"},{"year":"2020","author":"Oktay","journal-title":"Scalable model compression by entropy penalized reparameterization","key":"ref15"},{"volume-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library.","year":"2019","author":"Paszke","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/s11263-015-0816-y"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"year":"2020","author":"Stock","journal-title":"And the bit goes down: Revisiting the quantization of neural networks","key":"ref19"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1016\/j.neucom.2021.07.022"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/JSTSP.2020.2969554"},{"key":"ref22","article-title":"Fracbits: Mixed precision quantization via fractional bit-widths","author":"Yang","year":"2020","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TIT.1978.1055934"}],"event":{"name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2024,5,19]]},"location":"Singapore, Singapore","end":{"date-parts":[[2024,5,22]]}},"container-title":["2024 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10557746\/10557828\/10558050.pdf?arnumber=10558050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T06:58:08Z","timestamp":1719989888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10558050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,19]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iscas58744.2024.10558050","relation":{},"subject":[],"published":{"date-parts":[[2024,5,19]]}}}