{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:37Z","timestamp":1740101797825,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097231","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["M22: Rate-Distortion Inspired Gradient Compression"],"prefix":"10.1109","author":[{"given":"Yangyi","family":"Liu","sequence":"first","affiliation":[{"name":"McMaster University,Electrical and Computer Engineering Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadaf","family":"Salehkalaibar","sequence":"additional","affiliation":[{"name":"McMaster University,Electrical and Computer Engineering Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Rini","sequence":"additional","affiliation":[{"name":"National Yang-Ming Chiao-Tung University (NYCU),Electrical and Computer Engineering Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"McMaster University,Electrical and Computer Engineering Department"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/090759574"},{"key":"ref2","first-page":"9850","article-title":"Atomo: Communication-efficient learning via atomic sparsification","author":"Wang","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","first-page":"5973","article-title":"The convergence of sparsified gradient methods","author":"Alistarh","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174245"},{"key":"ref5","first-page":"4448","article-title":"Sparsified SGD with memory","author":"Stich","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"article-title":"Federated learning: Strategies for improving communication efficiency","year":"2016","author":"Kone\u010dn\u00fd","key":"ref7"},{"article-title":"vqSGD: Vector quantized stochastic gradient descent","year":"2019","author":"Gandikota","key":"ref8"},{"key":"ref9","first-page":"560","article-title":"signSGD: Compressed optimization for non-convex problems","author":"Bernstein","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"7564","article-title":"cpSGD: Communication-efficient and differentially-private distributed SGD","volume-title":"32nd Advances in Neural Information Processing Systems (NIPS)","author":"Agarwal"},{"article-title":"Privacy for free: Communication efficient learning with differential privacy using sketches","year":"2019","author":"Li","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icc45855.2022.9838754"},{"key":"ref13","first-page":"3304","article-title":"Don\u2019t waste your bits! squeeze activations and gradients for deep neural networks via tinyscript","volume-title":"International Conference on Machine Learning","author":"Fu"},{"key":"ref14","first-page":"1273","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","author":"McMahan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref17","article-title":"A mean-field limit for certain deep neural networks","author":"Ara\u00fajo","year":"2019","journal-title":"arXiv preprint arXiv:1906.00193"},{"key":"ref18","article-title":"A rigorous framework for the mean field limit of multilayer neural networks","author":"Nguyen","year":"2020","journal-title":"arXiv preprint arXiv:2001.11443"},{"key":"ref19","article-title":"Successive pruning for model compression via rate distortion theory","author":"Isik","year":"2021","journal-title":"arXiv preprint arXiv:2102.08329"},{"key":"ref20","article-title":"Deep neural networks as gaussian processes","author":"Lee","year":"2017","journal-title":"arXiv preprint arXiv:1711.00165"},{"key":"ref21","article-title":"Gaussian process behaviour in wide deep neural networks","author":"Matthews","year":"2018","journal-title":"arXiv preprint arXiv:1804.11271"},{"key":"ref22","article-title":"The convergence of sparsified gradient methods","author":"Alistarh","year":"2018","journal-title":"arXiv preprint arXiv:1809.10505"},{"key":"ref23","first-page":"5976","article-title":"The convergence of sparsified gradient methods","volume-title":"Advances in Neural Information Processing Systems 31","author":"Alistarh","year":"2018"},{"key":"ref24","article-title":"QSGD: Randomized quantization for communication-optimal stochastic gradient descent","volume-title":"CoRR","author":"Alistarh","year":"2016"},{"key":"ref25","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"Wen","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30"},{"key":"ref26","first-page":"7662","article-title":"Communication compression for decentralized training","author":"Tang","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31."},{"article-title":"Layer-adaptive sparsity for the magnitude-based pruning","volume-title":"International Conference on Learning Representations","author":"Lee","key":"ref27"},{"key":"ref28","article-title":"Communication-efficient distributed SGD with sketching","volume-title":"Advances in Neural Information Processing Systems","author":"Ivkin","year":"2019"},{"key":"ref29","article-title":"M22: A communication-efficient algorithm for federated learning inspired by rate-distortion","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2301.09269"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097231.pdf?arnumber=10097231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:57:19Z","timestamp":1709247439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097231","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}