{"id":"https://openalex.org/W7224935692","doi":"https://doi.org/10.48550/arxiv.2610.39902","title":"CovFedAvg: Local Low-Loss Curves and Federated Model Selection","display_name":"CovFedAvg: Local Low-Loss Curves and Federated Model Selection","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224935692","doi":"https://doi.org/10.48550/arxiv.2610.39902"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39902","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39902","pdf_url":"https://arxiv.org/pdf/2610.39902","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39902","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064149718","display_name":"Federico Lucchetti","orcid":"https://orcid.org/0000-0001-9778-8460","observed_orcids":["https://orcid.org/0000-0001-9778-8460"]},"institutions":[{"id":"https://openalex.org/I2802229882","display_name":"Centre Hospitalier Universitaire Vaudois","ror":"https://ror.org/05a353079","country_code":"CH","type":"healthcare","lineage":["https://openalex.org/I2802229882"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lucchetti, Federico","raw_affiliation_strings":["Center for Psychiatric Neuroscience , Department of Psychiatry , Lausanne University Hospital and the"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Psychiatric Neuroscience , Department of Psychiatry , Lausanne University Hospital and the","institution_ids":["https://openalex.org/I2802229882"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005578675","display_name":"Marcus V\u00f6lp","orcid":"https://orcid.org/0000-0002-8020-4446","observed_orcids":["https://orcid.org/0000-0002-8020-4446"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]},{"id":"https://openalex.org/I97565354","display_name":"University of Lausanne","ror":"https://ror.org/019whta54","country_code":"CH","type":"education","lineage":["https://openalex.org/I97565354"]}],"countries":["CH","LU"],"is_corresponding":false,"raw_author_name":"V\u00f6lp, Marcus","raw_affiliation_strings":["Interdisciplinary Centre for Security, Reliability and Trust (SnT) , University of Luxembourg , Luxembourg","University of Lausanne , Lausanne , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Centre for Security, Reliability and Trust (SnT) , University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]},{"raw_affiliation_string":"University of Lausanne , Lausanne , Switzerland","institution_ids":["https://openalex.org/I97565354"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994999766349792,"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":0.9994999766349792,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.00019999999494757503,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/federated-learning","display_name":"federated learning","score":0.8769999742507935},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.7239999771118164},{"id":"https://openalex.org/keywords/fedavg","display_name":"FedAvg","score":0.746999979019165},{"id":"https://openalex.org/keywords/gradient-aggregation","display_name":"gradient aggregation","score":0.5090000033378601},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"activity recognition","score":0.8610000014305115},{"id":"https://openalex.org/keywords/privacy-preserving-federated-learning","display_name":"privacy-preserving federated learning","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6565999984741211},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5350000262260437},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2780771206","wikidata":"https://www.wikidata.org/wiki/Q3271761","display_name":"Safeguard","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2612999975681305},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C15845906","wikidata":"https://www.wikidata.org/wiki/Q1172338","display_name":"Data exchange","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39902","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39902","pdf_url":"https://arxiv.org/pdf/2610.39902","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39902","doi":"https://doi.org/10.48550/arxiv.2610.39902","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39902","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39902","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39902","pdf_url":"https://arxiv.org/pdf/2610.39902","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224935692.pdf","grobid_xml":"https://content.openalex.org/works/W7224935692.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3203913075","https://openalex.org/W7213958477","https://openalex.org/W7133216270","https://openalex.org/W4401863680","https://openalex.org/W4312931336","https://openalex.org/W4285101059","https://openalex.org/W7213257108","https://openalex.org/W7162013894","https://openalex.org/W4285031788","https://openalex.org/W3153875449"],"abstract_inverted_index":{"Clients":[0],"observing":[1],"different":[2],"parts":[3],"of":[4],"a":[5,30,44,91,111,136,195],"prediction":[6],"task":[7],"may":[8],"learn":[9],"locally":[10],"equivalent":[11],"models":[12,24,37],"with":[13],"incompatible":[14],"behavior":[15],"outside":[16],"their":[17],"observed":[18],"support.":[19],"We":[20,98],"study":[21],"whether":[22],"redundant":[23],"permit":[25],"local":[26,36],"low-loss":[27],"paths":[28],"toward":[29],"compatible":[31],"shared":[32,125],"model.":[33],"CovFedAvg":[34,167],"retains":[35],"and":[38,51,83,102,105,110,143,145,158,186,213],"curve":[39],"controls":[40],"on":[41],"clients,":[42],"fits":[43],"common":[45],"endpoint":[46],"through":[47],"aggregated":[48],"gradient":[49],"contributions,":[50],"selects":[52],"an":[53],"actual":[54],"candidate":[55],"model":[56,82],"using":[57],"distributed":[58,179],"training":[59,77],"losses.":[60],"No":[61],"centralized":[62],"calibration":[63,162],"examples":[64],"or":[65,95],"client-to-client":[66],"sample":[67],"exchange":[68],"are":[69],"required.":[70],"Exact":[71],"selection":[72],"guarantees":[73],"no":[74],"higher":[75],"evaluated":[76],"loss":[78],"than":[79],"the":[80,84,124],"previous":[81],"current-round":[85],"FedAvg":[86],"candidate;":[87],"this":[88],"is":[89],"not":[90,193],"global-optimality,":[92],"stationarity,":[93],"generalization,":[94],"differential-privacy":[96],"guarantee.":[97],"state":[99],"conditional":[100],"client-compatibility":[101],"approximate-selection":[103],"bounds":[104],"retain":[106],"corrected":[107],"transformation":[108],"identities":[109],"separate":[112],"full-gradient":[113],"safeguard":[114],"theorem":[115],"for":[116],"reference":[117],"algorithms.":[118],"A":[119],"complementary":[120],"input-support":[121],"example":[122],"recovers":[123],"absolute-value":[126],"regression,":[127],"while":[128],"matched":[129,178],"direct":[130],"fine-tuning":[131,180],"also":[132],"solves":[133],"it.":[134],"Across":[135],"synthetic":[137],"support":[138,184],"task,":[139],"recorded":[140],"activity-recognition":[141],"subjects,":[142],"participating":[144],"future":[146],"gas-sensor":[147],"batches,":[148],"we":[149],"evaluate":[150],"five":[151,153],"methods,":[152],"seeds,":[154],"two":[155],"network":[156],"widths,":[157],"20":[159],"rounds":[160],"without":[161],"data.":[163],"At":[164],"width":[165],"16,":[166],"raises":[168],"participating-Gas":[169],"macro":[170],"balanced":[171],"accuracy":[172],"from":[173],"FedAvg's":[174],"88.88%":[175],"to":[176],"89.84%;":[177],"reaches":[181],"91.65%.":[182],"Results":[183],"feasibility":[185],"modest":[187],"gains":[188],"over":[189,198],"FedAvg,":[190],"but":[191],"do":[192],"establish":[194,205],"curve-specific":[196],"advantage":[197],"equally":[199],"costly":[200],"optimization.":[201],"Exact-sum":[202],"numerical":[203],"experiments":[204],"data":[206],"flow;":[207],"end-to-end":[208],"privacy":[209],"requires":[210],"additional":[211],"mechanisms":[212],"analysis.":[214]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}