{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:10:11Z","timestamp":1766733011472,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"publisher","award":["W911NF1910232"],"award-info":[{"award-number":["W911NF1910232"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MIUR (Italian Ministry for Education and Research) under the initiative \u201cDepartments of Excellence\u201d"},{"DOI":"10.13039\/501100000781","name":"European Research Council (ERC) through Project BEACON","doi-asserted-by":"publisher","award":["677854"],"award-info":[{"award-number":["677854"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"U.K. EPSRC","doi-asserted-by":"publisher","award":["EPSRC-EP\/T023600\/1","EPSRC-EP\/W035960\/1"],"award-info":[{"award-number":["EPSRC-EP\/T023600\/1","EPSRC-EP\/W035960\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/jsait.2022.3231459","type":"journal-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:25:21Z","timestamp":1672082721000},"page":"789-802","source":"Crossref","is-referenced-by-count":10,"title":["Rate-Constrained Remote Contextual Bandits"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0116-8852","authenticated-orcid":false,"given":"Francesco","family":"Pase","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Information Processing and Communications Lab, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7725-395X","authenticated-orcid":false,"given":"Deniz","family":"G\u00fcnd\u00fcz","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Information Processing and Communications Lab, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-4678","authenticated-orcid":false,"given":"Michele","family":"Zorzi","sequence":"additional","affiliation":[{"name":"Human Inspired Technology Center and the Department of Information Engineering, University of Padova, Padua, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2646342"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-9568.2011.07980.x"},{"key":"ref12","article-title":"Informationtheoretic lower bounds for distributed statistical estimation with communication constraints","volume":"26","author":"zhang","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"13956","article-title":"Generalization in reinforcement learning with selective noise injection and information bottleneck","volume":"32","author":"igl","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/2371219"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref36","article-title":"Thompson sampling and approximate inference","author":"phan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"29984","article-title":"Batched Thompson sampling","volume":"34","author":"kalkanli","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Multi-agent multiarmed bandits with limited communication","author":"agarwal","year":"2021","journal-title":"arXiv 2102 08462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1986.1057194"},{"key":"ref33","first-page":"1","article-title":"Learning robust representations via multi-view information bottleneck","author":"federici","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","article-title":"Decentralized estimation and decision theory","author":"berger","year":"1979","journal-title":"Proc IEEE 7th Spring Workshop Inf Theory"},{"key":"ref32","volume":"74","author":"lai","year":"2021","journal-title":"The Psychology of Learning and Motivation Advances in Research Theory"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.9"},{"key":"ref17","article-title":"Efficient parallel methods for deep reinforcement learning","author":"clemente","year":"2017","journal-title":"arXiv 1705 04862"},{"key":"ref39","article-title":"Observations analytiques","volume":"1","author":"lambert","year":"1770","journal-title":"Nouveaux Mémoires de LAcadémie Royale Des Sciences et Belles-Lettres"},{"key":"ref16","article-title":"GA3C: GPU-based A3C for deep reinforcement learning","author":"babaeizadeh","year":"2016","journal-title":"Proc Neural Inf Process Syst Workshop"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.889015"},{"key":"ref19","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref18","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"arXiv 1605 06676"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2967566"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852451"},{"key":"ref45","first-page":"205","article-title":"Information geometry and alternating minimization procedures","volume":"1","author":"csisz\u00e1r","year":"1984","journal-title":"Stat Decisions Supplementary"},{"key":"ref26","first-page":"1","article-title":"What is the state of neural network pruning?","author":"blalock","year":"2021","journal-title":"Proc 3rd MLSys Conf"},{"key":"ref25","first-page":"1","article-title":"Single-shot pruning for offline reinforcement learning","author":"arnob","year":"2021","journal-title":"Proc Neural Inf Process Syst Workshop Offline Reinforcement Learn"},{"key":"ref20","article-title":"Emergence of language with multi-agent games: Learning to communicate with sequences of symbols","author":"havrylov","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0650"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/11602613_102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087248"},{"key":"ref44","first-page":"1417","article-title":"Simple Bayesian algorithms for best arm identification","author":"russo","year":"2016","journal-title":"Proc 29th Annu Conf Learn Theory"},{"key":"ref21","article-title":"Multi-agent cooperation and the emergence of (natural) language","author":"lazaridou","year":"2017","journal-title":"arXiv 1612 07182"},{"key":"ref43","article-title":"Asymptotic convergence of Thompson sampling","author":"kalkanli","year":"2020","journal-title":"arXiv 2011 03917"},{"key":"ref28","first-page":"1","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref27","article-title":"An information-theoretic justification for model pruning","author":"isik","year":"2021","journal-title":"arXiv 2102 08329"},{"key":"ref29","first-page":"11215","article-title":"Solving multi-arm bandit using a few bits of communication","author":"hanna","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref8","first-page":"1856","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref7","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"levine","year":"2018","journal-title":"arXiv 1805 00909"},{"journal-title":"Elements of Information Theory","year":"2006","author":"cover","key":"ref9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2941458"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118346"},{"key":"ref6","first-page":"1","article-title":"InfoBot:Transfer and exploration via the information bottleneck","author":"goyal","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","article-title":"The information bottleneck method","author":"tishby","year":"2000","journal-title":"arXiv physics\/0004057"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/10153453\/09998994.pdf?arnumber=9998994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:37:56Z","timestamp":1688409476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9998994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":46,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2022.3231459","relation":{},"ISSN":["2641-8770"],"issn-type":[{"type":"electronic","value":"2641-8770"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}