{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:10:41Z","timestamp":1774717841713,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,2,2]],"date-time":"2020-02-02T00:00:00Z","timestamp":1580601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,2]],"date-time":"2020-02-02T00:00:00Z","timestamp":1580601600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,2]],"date-time":"2020-02-02T00:00:00Z","timestamp":1580601600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,2,2]]},"DOI":"10.1109\/ita50056.2020.9245017","type":"proceedings-article","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T22:10:58Z","timestamp":1604700658000},"page":"1-28","source":"Crossref","is-referenced-by-count":9,"title":["Communication-Efficient and Byzantine-Robust Distributed Learning"],"prefix":"10.1109","author":[{"given":"Avishek","family":"Ghosh","sequence":"first","affiliation":[]},{"given":"Raj Kumar","family":"Maity","sequence":"additional","affiliation":[]},{"given":"Swanand","family":"Kadhe","sequence":"additional","affiliation":[]},{"given":"Arya","family":"Mazumdar","sequence":"additional","affiliation":[]},{"given":"Kannan","family":"Ramchandran","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"7074","article-title":"Defending against saddle point attack in Byzantine-robust distributed learning","author":"yin","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref32","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","author":"yin","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref31","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"},{"key":"ref30","article-title":"Lecture notes for ece598yw:Information-theoretic methods for high-dimensional statistics","author":"wu","year":"2017"},{"key":"ref34","first-page":"2328","article-title":"Information-theoretic lower bounds for distributed statistical estimation with communication constraints","author":"zhang","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"19","article-title":"Aggregathor: Byzantine machine learning via robust gradient aggregation","author":"damaskinos","year":"2019","journal-title":"Published in the Conference on Systems and Machine Learning (SysML) 2019"},{"key":"ref11","article-title":"Distributed robust learning","author":"feng","year":"2014"},{"key":"ref12","article-title":"Robust federated learning in a heterogeneous environment","author":"ghosh","year":"2019"},{"key":"ref13","article-title":"vqsgd:Vector quantized stochastic gradient descent","author":"gandikota","year":"2019"},{"key":"ref14","first-page":"arxiv:1904.05115","article-title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","author":"horva\u00b4th","year":"2019"},{"key":"ref15","article-title":"Communication-efficient distributed sgd with sketching","author":"ivkin","year":"2019"},{"key":"ref16","article-title":"Federated learning:Strategies for improving communication efficiency","author":"kone?n?","year":"2016"},{"key":"ref17","article-title":"Error feedback fixes signsgd and other gradient compression schemes","author":"karimireddy","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006962"},{"key":"ref28","article-title":"Introduction to the non-asymptotic analysis of random matrices","author":"vershynin","year":"2010"},{"key":"ref4","article-title":"Byzantine-tolerant machine learning","author":"blanchard","year":"2017"},{"key":"ref27","first-page":"3329","article-title":"Distributed mean estimation with limited communication","volume":"70","author":"suresh","year":"0"},{"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":"ref6","article-title":"signsgd:Compressed optimisation for non-convex problems","author":"bernstein","year":"2018"},{"key":"ref29","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":"ref5","article-title":"signsgd: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018"},{"key":"ref8","article-title":"R2c2:A network stack for rack-scale computers","author":"costa","year":"2015","journal-title":"SIGCOMM 2015"},{"key":"ref7","article-title":"signsgd with majority vote is communication efficient and byzantine fault tolerant","author":"bernstein","year":"2018"},{"key":"ref2","article-title":"Communicationefficient stochastic gradient descent, with applications to neural networks","author":"alistarh","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref1","first-page":"1709","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref22","article-title":"AWS news blog","year":"0"},{"key":"ref21","article-title":"The hidden vulnerability of distributed learning in byzantium","author":"mhamdi","year":"2018"},{"key":"ref24","article-title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns","author":"seide","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref23","first-page":"4447","article-title":"Sparsified sgd with memory","author":"stich","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2933057.2933105"},{"key":"ref25","article-title":"Scalable distributed dnn training using commodity gpu cloud computing","author":"strom","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"}],"event":{"name":"2020 Information Theory and Applications Workshop (ITA)","location":"San Diego, CA, USA","start":{"date-parts":[[2020,2,2]]},"end":{"date-parts":[[2020,2,7]]}},"container-title":["2020 Information Theory and Applications Workshop (ITA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9244865\/9244867\/09245017.pdf?arnumber=9245017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:51:09Z","timestamp":1656453069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9245017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,2]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ita50056.2020.9245017","relation":{},"subject":[],"published":{"date-parts":[[2020,2,2]]}}}