{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T10:17:07Z","timestamp":1768472227301,"version":"3.49.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"22","license":[{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T00:00:00Z","timestamp":1668470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"FORMAS Project entitled \u201cIntelligent Energy Management in Smart Community With Distributed Machine Learning\u201d","award":["2021-00306"],"award-info":[{"award-number":["2021-00306"]}]},{"name":"Swedish Research Council Project entitled \u201cCoding for Large-Scale Distributed Machine Learning\u201d","award":["2021-04772"],"award-info":[{"award-number":["2021-04772"]}]},{"name":"STINT Project \u201cEfficient and Secure Distributed Machine Learning With Gradient Descend\u201d","award":["CH2019-8333"],"award-info":[{"award-number":["CH2019-8333"]}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-2107216"],"award-info":[{"award-number":["CNS-2107216"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-2128368"],"award-info":[{"award-number":["CNS-2128368"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2022,11,15]]},"DOI":"10.1109\/jiot.2022.3187067","type":"journal-article","created":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T19:45:07Z","timestamp":1656531907000},"page":"22958-22971","source":"Crossref","is-referenced-by-count":10,"title":["Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge IoT"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9878-3722","authenticated-orcid":false,"given":"Wanlu","family":"Lei","sequence":"first","affiliation":[{"name":"Interconnection Design in Baseband and Interconnect Department, Ericsson AB, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4686-0973","authenticated-orcid":false,"given":"Yu","family":"Ye","sequence":"additional","affiliation":[{"name":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5407-0835","authenticated-orcid":false,"given":"Ming","family":"Xiao","sequence":"additional","affiliation":[{"name":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7926-5081","authenticated-orcid":false,"given":"Mikael","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Division of Information Science and Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6606-5822","authenticated-orcid":false,"given":"Zhu","family":"Han","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Houston, Houston, TX, USA"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Stochastic ADMM for nonsmooth optimization","author":"ouyang","year":"2012","journal-title":"arXiv 1211 0632"},{"key":"ref38","author":"strang","year":"2019","journal-title":"Linear Algebra and Learning from Data"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2005.843546"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/14096668X"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/130943170"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2983167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2907258"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2304432"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2937496"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2839589"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-020-00007-x"},{"key":"ref29","article-title":"Communication-efficient policy gradient methods for distributed reinforcement learning","author":"chen","year":"2019","journal-title":"arXiv 1812 03239"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3007070"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref21","first-page":"1008","article-title":"Actor–critic algorithms","author":"konda","year":"2000","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref24","author":"bertsekas","year":"2019","journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878435"},{"key":"ref26","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"arXiv 1507 04296"},{"key":"ref50","author":"deisenroth","year":"2013","journal-title":"A Survey on Policy Search for Robotics"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2885453"},{"key":"ref55","first-page":"3","article-title":"Incremental gradient, subgradient, and proximal methods for convex optimization: A survey","author":"bertsekas","year":"2011","journal-title":"Opt Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MetroAgriFor50201.2020.9277630"},{"key":"ref53","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref52","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2992628"},{"key":"ref40","first-page":"2839","article-title":"Faster stochastic alternating direction method of multipliers for nonconvex optimization","author":"huang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000396"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2712560"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3143488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.09.017"},{"key":"ref16","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"arXiv 1610 03295"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref18","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1900630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000116"},{"key":"ref5","article-title":"Deploying federated learning in large-scale cellular networks: Spatial convergence analysis","author":"lin","year":"2021","journal-title":"arXiv 2103 06056"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2993703"},{"key":"ref49","first-page":"4897","article-title":"Lyapunov functions for first-order methods: Tight automated convergence guarantees","author":"taylor","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2767608"},{"key":"ref46","first-page":"613","article-title":"CADA: Communication-adaptive distributed adam","author":"chen","year":"2021","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref45","article-title":"Stochastic recursive momentum for policy gradient methods","author":"yuan","year":"2020","journal-title":"arXiv 2003 04302"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3923\/itj.2006.851.859"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3058116"},{"key":"ref42","article-title":"Stochastic variance-reduced policy gradient","author":"papini","year":"2018","journal-title":"arXiv 1806 05618"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10843"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3027917"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6488907\/9939125\/9810334-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9939125\/09810334.pdf?arnumber=9810334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:02:36Z","timestamp":1670281356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9810334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,15]]},"references-count":56,"journal-issue":{"issue":"22"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2022.3187067","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,15]]}}}