{"id":"https://openalex.org/W4289713236","doi":"https://doi.org/10.1109/isit50566.2022.9834894","title":"Fundamental Limits of Personalized Federated Linear Regression with Data Heterogeneity","display_name":"Fundamental Limits of Personalized Federated Linear Regression with Data Heterogeneity","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289713236","doi":"https://doi.org/10.1109/isit50566.2022.9834894"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834894","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-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/A5055856459","display_name":"Chun-Ying Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Ying Hou","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080524212","display_name":"I-Hsiang Wang","orcid":"https://orcid.org/0000-0003-0695-5724"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Hsiang Wang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055856459"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05440415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9941999912261963,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9941999912261963,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9853000044822693,"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/computer-science","display_name":"Computer science","score":0.6997708082199097},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.5115493535995483},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4196714162826538},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35405653715133667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15889644622802734},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09458008408546448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997708082199097},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.5115493535995483},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4196714162826538},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35405653715133667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15889644622802734},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09458008408546448}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit50566.2022.9834894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834894","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1805361780","https://openalex.org/W2110091014","https://openalex.org/W2976335444","https://openalex.org/W2990789643","https://openalex.org/W2995473418","https://openalex.org/W3007345209","https://openalex.org/W3007548213","https://openalex.org/W3012968339","https://openalex.org/W3021654819","https://openalex.org/W3035870018","https://openalex.org/W3080269548","https://openalex.org/W3134581569","https://openalex.org/W3173537849","https://openalex.org/W4225854252","https://openalex.org/W4285876308","https://openalex.org/W4287906413","https://openalex.org/W4300427714","https://openalex.org/W4318619660","https://openalex.org/W4361192893","https://openalex.org/W6676587327","https://openalex.org/W6728757088","https://openalex.org/W6738383168","https://openalex.org/W6768570320","https://openalex.org/W6770590064","https://openalex.org/W6771501805","https://openalex.org/W6772318479","https://openalex.org/W6774120287","https://openalex.org/W6774195376","https://openalex.org/W6774978782","https://openalex.org/W6779269186","https://openalex.org/W6780030762","https://openalex.org/W6783516525","https://openalex.org/W6791102956","https://openalex.org/W6791913944","https://openalex.org/W6803863347"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Federated":[0],"learning":[1,9,113],"is":[2,26,36,131],"a":[3,37],"nascent":[4],"framework":[5],"for":[6],"collaborative":[7],"machine":[8],"over":[10],"networks":[11],"of":[12,28,81,87,109,138],"devices":[13,25],"with":[14],"local":[15,18],"data":[16,48,51,66,110],"and":[17,49,115,123],"model":[19],"updates.":[20],"Data":[21],"heterogeneity":[22,52,111],"across":[23,67],"the":[24,29,45,60,65,82,98,107,116,128,132,136],"one":[27],"challenges":[30],"confronting":[31],"this":[32,56],"emerging":[33],"field.":[34],"Personalization":[35],"natural":[38],"approach":[39],"to":[40],"simultaneously":[41],"utilize":[42],"information":[43],"from":[44,71],"other":[46],"users\u2019":[47],"take":[50],"into":[53],"account.":[54],"In":[55],"work,":[57],"we":[58],"study":[59],"linear":[61,89],"regression":[62,73],"problem":[63,121],"where":[64],"users":[68],"are":[69],"generated":[70],"different":[72],"vectors.":[74],"We":[75,91],"present":[76],"an":[77,93],"information-theoretic":[78],"lower":[79,99],"bound":[80,95,100],"minimax":[83],"expected":[84],"excess":[85],"risk":[86],"personalized":[88],"models.":[90],"show":[92],"upper":[94],"that":[96,127],"matches":[97],"within":[101],"constant":[102],"factors.":[103],"The":[104],"results":[105],"characterize":[106],"effect":[108],"on":[112],"performance":[114],"trade-off":[117],"between":[118],"sample":[119],"size,":[120],"difficulty,":[122],"distribution":[124],"discrepancy,":[125],"suggesting":[126],"discrepancy-to-difficulty":[129],"ratio":[130],"key":[133],"factor":[134],"governing":[135],"effectiveness":[137],"heterogeneous":[139],"data.":[140]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}