{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T10:21:20Z","timestamp":1773397280954,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council (ERC) under the European Unions Horizon 2020 Research and Innovation Program","doi-asserted-by":"publisher","award":["725731"],"award-info":[{"award-number":["725731"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Open Fellowship by the Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/twc.2022.3215663","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:24:15Z","timestamp":1667517855000},"page":"2946-2961","source":"Crossref","is-referenced-by-count":13,"title":["Wireless Federated Langevin Monte Carlo: Repurposing Channel Noise for Bayesian Sampling and Privacy"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7820-9531","authenticated-orcid":false,"given":"Dongzhu","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9898-3209","authenticated-orcid":false,"given":"Osvaldo","family":"Simeone","sequence":"additional","affiliation":[{"name":"Department of Engineering, King's College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"A complete recipe for stochastic gradient MCMC","volume":"28","author":"ma","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/9781680832198"},{"key":"ref15","first-page":"13012","article-title":"On the convergence of Hamiltonian Monte Carlo with stochastic gradients","author":"zou","year":"2021","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3150\/19-BEJ1178"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3103874"},{"key":"ref11","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"2016","journal-title":"arXiv 1612 01474"},{"key":"ref10","first-page":"1321","article-title":"On calibration of modern neural networks","author":"guo","year":"2017","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref16","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024629"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737464"},{"key":"ref51","article-title":"Federated learning over noisy channels: Convergence analysis and design examples","author":"wei","year":"2021","journal-title":"arXiv 2101 02198"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102388"},{"key":"ref46","article-title":"Wireless federated Langevin Monte Carlo: Repurposing channel noise for Bayesian sampling and privacy","author":"liu","year":"2021","journal-title":"arXiv 2108 07644"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2999606"},{"key":"ref48","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref47","article-title":"Gaussian word embedding with a Wasserstein distance loss","author":"sun","year":"2018","journal-title":"arXiv 1808 07016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref41","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3015671"},{"key":"ref43","first-page":"13773","article-title":"Understanding gradient clipping in private SGD: A geometric perspective","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref49","article-title":"FedCos: A scene-adaptive federated optimization enhancement for performance improvement","author":"zhang","year":"2022","journal-title":"arXiv 2204 03174"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"dwork","year":"2014","journal-title":"Found Trends Theor Comput Sci"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3039309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322199"},{"key":"ref4","article-title":"Revisiting analog over-the-air machine learning: The blessing and curse of interference","author":"yang","year":"2021","journal-title":"arXiv 2107 11733"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090323"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036948"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946245"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900379"},{"key":"ref35","first-page":"678","article-title":"Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent","author":"dalalyan","year":"2017","journal-title":"Proc Conf Learn Theory (COLT)"},{"key":"ref34","first-page":"557","article-title":"On connecting stochastic gradient MCMC and differential privacy","author":"li","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref37","first-page":"1","article-title":"Variational consensus Monte Carlo","author":"rabinovich","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118406"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174426"},{"key":"ref30","first-page":"1","article-title":"cpSGD: Communication-efficient and differentially-private distributed SGD","author":"agarwal","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref33","first-page":"2493","article-title":"Privacy for free: Posterior sampling and stochastic gradient Monte Carlo","author":"wang","year":"2015","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC51858.2021.9593170"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900103"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2941458"},{"key":"ref39","first-page":"764","article-title":"On the theory of variance reduction for stochastic gradient Monte Carlo","author":"chatterji","year":"2018","journal-title":"Proc 22nd Int Conf Mach Learn (ICML)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176995476"},{"key":"ref24","article-title":"Data-free knowledge distillation for heterogeneous federated learning","author":"zhu","year":"2021","journal-title":"arXiv 2105 10056"},{"key":"ref23","first-page":"1","article-title":"FedBE: Making Bayesian model ensemble applicable to federated learning","author":"chen","year":"2021","journal-title":"Proc Intl Conf Learn Represent (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3168490"},{"key":"ref25","article-title":"Variational federated multi-task learning","author":"corinzia","year":"2019","journal-title":"arXiv 1906 06268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2989580"},{"key":"ref22","article-title":"Bayesian federated learning over wireless networks","author":"lee","year":"2020","journal-title":"arXiv 2012 15486"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118348"},{"key":"ref28","article-title":"QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning","author":"vono","year":"2021","journal-title":"arXiv 2106 00797"},{"key":"ref27","first-page":"1703","article-title":"Federated stochastic gradient Langevin dynamics","author":"el mekkaoui","year":"2021","journal-title":"Proc 37th Conf Uncertain Artif Intell (UAI)"},{"key":"ref29","article-title":"VqSGD: Vector quantized stochastic gradient descent","author":"gandikota","year":"2019","journal-title":"arXiv 1911 07971"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10122187\/09930942.pdf?arnumber=9930942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:28:04Z","timestamp":1686594484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9930942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":52,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/twc.2022.3215663","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}