{"id":"https://openalex.org/W4392175515","doi":"https://doi.org/10.1109/globecom54140.2023.10437650","title":"Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics","display_name":"Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4392175515","doi":"https://doi.org/10.1109/globecom54140.2023.10437650"},"language":"en","primary_location":{"id":"doi:10.1109/globecom54140.2023.10437650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom54140.2023.10437650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/70613.html>,","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102982694","display_name":"Boning Zhang","orcid":"https://orcid.org/0000-0001-8516-137X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Boning Zhang","raw_affiliation_strings":["School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038776407","display_name":"Dongzhu Liu","orcid":"https://orcid.org/0000-0001-7820-9531"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dongzhu Liu","raw_affiliation_strings":["School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017736224","display_name":"Osvaldo Simeone","orcid":"https://orcid.org/0000-0001-9898-3209"},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Osvaldo Simeone","raw_affiliation_strings":["King's College,Department of Engineering,London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College,Department of Engineering,London","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004583148","display_name":"Guangxu Zhu","orcid":"https://orcid.org/0000-0001-9532-9201"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangxu Zhu","raw_affiliation_strings":["Shenzhen Research Institute of Big Data"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5286","last_page":"5291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10964","display_name":"Wireless Communication Security Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/langevin-dynamics","display_name":"Langevin dynamics","score":0.7397377490997314},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5445071458816528},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.5165025591850281},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.48751136660575867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48063817620277405},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45173415541648865},{"id":"https://openalex.org/keywords/langevin-equation","display_name":"Langevin equation","score":0.4428645074367523},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3185366988182068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21677449345588684},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11591106653213501},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08656072616577148}],"concepts":[{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.7397377490997314},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5445071458816528},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.5165025591850281},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.48751136660575867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48063817620277405},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45173415541648865},{"id":"https://openalex.org/C2777577648","wikidata":"https://www.wikidata.org/wiki/Q584537","display_name":"Langevin equation","level":2,"score":0.4428645074367523},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3185366988182068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21677449345588684},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11591106653213501},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08656072616577148}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globecom54140.2023.10437650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom54140.2023.10437650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:305419","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/70613.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:305419","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/70613.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6922287014","display_name":null,"funder_award_id":"EP/W024101/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2963932270","https://openalex.org/W2981138228","https://openalex.org/W2995053006","https://openalex.org/W3088234149","https://openalex.org/W3102100346","https://openalex.org/W3111192549","https://openalex.org/W3164731060","https://openalex.org/W3194214002","https://openalex.org/W3201665951","https://openalex.org/W3213161637","https://openalex.org/W4221153504","https://openalex.org/W4294825671","https://openalex.org/W4297687186","https://openalex.org/W4317927903","https://openalex.org/W4367189808","https://openalex.org/W4372348964","https://openalex.org/W6600144256","https://openalex.org/W6684809622","https://openalex.org/W6728757088","https://openalex.org/W6736725445","https://openalex.org/W6739651123","https://openalex.org/W6773555910","https://openalex.org/W6773817997","https://openalex.org/W6797113401","https://openalex.org/W6811287140","https://openalex.org/W6845962869"],"related_works":["https://openalex.org/W4387774682","https://openalex.org/W2155468644","https://openalex.org/W4388714455","https://openalex.org/W2080085730","https://openalex.org/W3098261380","https://openalex.org/W3094412134","https://openalex.org/W2135598349","https://openalex.org/W2999738544","https://openalex.org/W2003871724","https://openalex.org/W2214421583"],"abstract_inverted_index":{"The":[0],"recent":[1],"development":[2],"of":[3,14,43,56,117],"scalable":[4],"Bayesian":[5,15,51,92],"inference":[6],"methods":[7],"has":[8],"renewed":[9],"interest":[10],"in":[11,53,73,115,160],"the":[12,54,118,123,129,140],"adoption":[13],"learning":[16,23,52],"as":[17,40],"an":[18],"alternative":[19],"to":[20],"conventional":[21],"frequentist":[22],"that":[24,46,70],"offers":[25],"improved":[26],"model":[27],"calibration":[28],"via":[29],"uncertainty":[30],"quantification.":[31],"Recently,":[32],"federated":[33,44],"averaging":[34,45],"Langevin":[35],"dynamics":[36],"(FALD)":[37],"was":[38],"introduced":[39],"a":[41,67],"variant":[42],"can":[47,148],"efficiently":[48],"implement":[49],"distributed":[50],"presence":[55],"noiseless":[57],"communications.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"wireless":[64,74,91],"FALD":[65,72],"(WFALD),":[66],"novel":[68],"protocol":[69],"realizes":[71],"systems":[75],"by":[76,108,126],"integrating":[77],"over-the-air":[78],"computation":[79],"and":[80,103,128,135],"channel-driven":[81],"sampling":[82],"for":[83,152],"Monte":[84,153],"Carlo":[85,154],"updates.":[86],"Unlike":[87],"prior":[88],"work":[89],"on":[90],"learning,":[93],"WFALD":[94,127],"enables":[95],"(i)":[96],"multiple":[97],"local":[98],"updates":[99],"between":[100,122],"communication":[101],"rounds;":[102],"(ii)":[104],"stochastic":[105],"gradients":[106],"computed":[107],"mini-batch.":[109],"A":[110],"convergence":[111],"analysis":[112],"is":[113,143],"presented":[114],"terms":[116],"2-":[119],"Wasserstein":[120],"distance":[121],"samples":[124],"produced":[125],"targeted":[130],"global":[131],"posterior":[132],"distribution.":[133],"Analysis":[134],"experiments":[136],"show":[137],"that,":[138],"when":[139],"signal-to-noise":[141],"ratio":[142],"sufficiently":[144],"large,":[145],"channel":[146],"noise":[147],"be":[149],"fully":[150],"repurposed":[151],"sampling,":[155],"thus":[156],"entailing":[157],"no":[158],"loss":[159],"performance.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}