{"id":"https://openalex.org/W4400644079","doi":"https://doi.org/10.1080/10618600.2024.2380051","title":"Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory","display_name":"Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4400644079","doi":"https://doi.org/10.1080/10618600.2024.2380051"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2024.2380051","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2024.2380051","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018587308","display_name":"Jiajun Liang","orcid":"https://orcid.org/0000-0002-2349-5371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Liang","raw_affiliation_strings":["ByteDance Inc","ByteDance Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]},{"raw_affiliation_string":"ByteDance Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101830434","display_name":"Qian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Department of Statistics, Purdue University","Department of Statistics, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Purdue University","institution_ids":[]},{"raw_affiliation_string":"Department of Statistics, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426957","display_name":"Wei Deng","orcid":"https://orcid.org/0000-0002-3671-5951"},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Deng","raw_affiliation_strings":["Machine Learning Research, Morgan Stanley","Machine Learning Research, Morgan Stanley, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Research, Morgan Stanley","institution_ids":["https://openalex.org/I2802755631"]},{"raw_affiliation_string":"Machine Learning Research, Morgan Stanley, New York, NY","institution_ids":["https://openalex.org/I2802755631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110373518","display_name":"Qifan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qifan Song","raw_affiliation_strings":["Department of Statistics, Purdue University","Department of Statistics, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Purdue University","institution_ids":[]},{"raw_affiliation_string":"Department of Statistics, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100761332","display_name":"Guang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guang Lin","raw_affiliation_strings":["Department of Mathematics & School of Mechanical Engineering, Purdue University","Department of Mathematics & School of Mechanical Engineering, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics & School of Mechanical Engineering, Purdue University","institution_ids":[]},{"raw_affiliation_string":"Department of Mathematics & School of Mechanical Engineering, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110373518"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.4803,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82123548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"34","issue":"2","first_page":"509","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hybrid-monte-carlo","display_name":"Hybrid Monte Carlo","score":0.6370446681976318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6227961182594299},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.603470504283905},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5834833383560181},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.5429352521896362},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4915076196193695},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4186832308769226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3991621434688568},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35230517387390137},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.3408324122428894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2860811948776245},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13796594738960266},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12558743357658386}],"concepts":[{"id":"https://openalex.org/C13153151","wikidata":"https://www.wikidata.org/wiki/Q1639846","display_name":"Hybrid Monte Carlo","level":4,"score":0.6370446681976318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227961182594299},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.603470504283905},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5834833383560181},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.5429352521896362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4915076196193695},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4186832308769226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991621434688568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35230517387390137},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3408324122428894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2860811948776245},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13796594738960266},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12558743357658386}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/10618600.2024.2380051","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2024.2380051","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G365424567","display_name":"TRUSTWORTHY HETEROGENEOUS DATA-AWARE BAYESIAN FEDERATED LEARNING","funder_award_id":"DESC0023161","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4275346382","display_name":"Collaborative Research: Robust Deep Learning in Real Physical Space: Generalization, Scalability, and Credibility","funder_award_id":"2134209","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G446273302","display_name":"Collaborative Research: Inference and Uncertainty Quantification for High Dimensional Systems in Remote Sensing: Methods, Computation, and Applications","funder_award_id":"2053746","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7109742449","display_name":"ASCENT: From sensors to multiscale digital twin to autonomous operation of resilient electric power grids","funder_award_id":"2328241","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7405926644","display_name":"Elements: FourPhonon: A Computational Tool for Higher-Order Phonon  Anharmonicity and Thermal Properties","funder_award_id":"2311848","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W621546036","https://openalex.org/W1524172054","https://openalex.org/W1545319692","https://openalex.org/W2044410728","https://openalex.org/W2059448777","https://openalex.org/W2073241381","https://openalex.org/W2116612304","https://openalex.org/W2167433878","https://openalex.org/W2222154095","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2590513847","https://openalex.org/W2596356468","https://openalex.org/W2604653582","https://openalex.org/W2736302961","https://openalex.org/W2788368350","https://openalex.org/W2902986194","https://openalex.org/W2913570153","https://openalex.org/W2920095265","https://openalex.org/W2947292840","https://openalex.org/W2963599479","https://openalex.org/W2970282196","https://openalex.org/W3003439716","https://openalex.org/W3005629823","https://openalex.org/W3006555759","https://openalex.org/W3012501605","https://openalex.org/W3021654819","https://openalex.org/W3030167577","https://openalex.org/W3038028469","https://openalex.org/W3040083890","https://openalex.org/W3040685212","https://openalex.org/W3086590218","https://openalex.org/W3090615085","https://openalex.org/W3092847086","https://openalex.org/W3100688298","https://openalex.org/W3118608800","https://openalex.org/W3170151574","https://openalex.org/W3172102279","https://openalex.org/W4225350188","https://openalex.org/W4226405495","https://openalex.org/W4247690662","https://openalex.org/W4249888970","https://openalex.org/W4288346227","https://openalex.org/W4308014763","https://openalex.org/W4310895557","https://openalex.org/W6631656437","https://openalex.org/W6638674303","https://openalex.org/W6681286327","https://openalex.org/W6739651123","https://openalex.org/W6759238902","https://openalex.org/W6764838729","https://openalex.org/W6772307254"],"related_works":["https://openalex.org/W2305965628","https://openalex.org/W4226314133","https://openalex.org/W1548972748","https://openalex.org/W3186706744","https://openalex.org/W227870709","https://openalex.org/W3087071515","https://openalex.org/W4294677683","https://openalex.org/W2959831473","https://openalex.org/W4323055853","https://openalex.org/W2291370119"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"a":[3],"novel":[4],"and":[5,23,41,57,59,68,74],"efficient":[6],"Bayesian":[7],"federated":[8],"learning":[9],"algorithm,":[10],"namely,":[11],"the":[12,38,48,60,65,72,83,91,110],"Federated":[13,112],"Averaging":[14],"stochastic":[15],"Hamiltonian":[16],"Monte":[17,114],"Carlo":[18,115],"(FA-HMC),":[19],"for":[20,98,120],"parameter":[21,51],"estimation":[22],"uncertainty":[24],"quantification.":[25],"We":[26],"establish":[27,82],"rigorous":[28],"convergence":[29,73,92],"guarantees":[30],"of":[31,50,62,77,85],"FA-HMC":[32,100,108],"on":[33,55,71],"non-iid":[34],"distributed":[35],"datasets,":[36],"under":[37],"strong":[39],"convexity":[40],"Hessian":[42],"smoothness":[43],"assumptions.":[44],"Our":[45],"analysis":[46,87],"investigates":[47],"effects":[49],"space":[52],"dimension,":[53],"noise":[54],"gradients":[56],"momentum,":[58],"frequency":[61],"communication":[63,75],"(between":[64],"central":[66],"node":[67],"local":[69],"nodes)":[70],"costs":[76],"FA-HMC.":[78],"Beyond":[79],"that,":[80],"we":[81],"tightness":[84],"our":[86],"by":[88],"showing":[89],"that":[90,107],"rate":[93],"cannot":[94],"be":[95],"improved":[96],"even":[97],"continuous":[99],"process.":[101],"Moreover,":[102],"extensive":[103],"empirical":[104],"studies":[105],"demonstrate":[106],"outperforms":[109],"existing":[111],"Averaging-Langevin":[113],"(FA-LD)":[116],"algorithm.":[117],"Supplementary":[118],"materials":[119],"this":[121],"article":[122],"are":[123],"available":[124],"online.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}