{"id":"https://openalex.org/W4387427566","doi":"https://doi.org/10.48550/arxiv.2310.03163","title":"FedNAR: Federated Optimization with Normalized Annealing Regularization","display_name":"FedNAR: Federated Optimization with Normalized Annealing Regularization","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4387427566","doi":"https://doi.org/10.48550/arxiv.2310.03163"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.03163","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03163","pdf_url":"https://arxiv.org/pdf/2310.03163","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.03163","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101548643","display_name":"Junbo Li","orcid":"https://orcid.org/0009-0002-2516-9227"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Junbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100589865","display_name":"Chong Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Chong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012361506","display_name":"Qirong Ho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Qirong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Eric P.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076700469","display_name":"Hongyi Wang","orcid":"https://orcid.org/0000-0003-4842-8754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongyi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101548643"],"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/T12676","display_name":"Machine Learning and ELM","score":0.9933000206947327,"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/T12676","display_name":"Machine Learning and ELM","score":0.9933000206947327,"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":0.9923999905586243,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/overfitting","display_name":"Overfitting","score":0.758536696434021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7052300572395325},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6666620969772339},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5684006214141846},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.4838196635246277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44466155767440796},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3985271453857422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37252551317214966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3206411898136139},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.301929771900177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16028988361358643}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.758536696434021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052300572395325},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6666620969772339},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5684006214141846},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.4838196635246277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44466155767440796},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3985271453857422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37252551317214966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206411898136139},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.301929771900177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16028988361358643}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.03163","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03163","pdf_url":"https://arxiv.org/pdf/2310.03163","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.03163","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.03163","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.03163","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03163","pdf_url":"https://arxiv.org/pdf/2310.03163","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387427566.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W4298369531","https://openalex.org/W3155135229"],"abstract_inverted_index":{"Weight":[0],"decay":[1,41,46,62,203],"is":[2,17,59,74,208],"a":[3,65,102,139],"standard":[4],"technique":[5],"to":[6,25,80,176,199],"improve":[7],"generalization":[8],"performance":[9],"in":[10,21,28,77,187],"modern":[11],"deep":[12],"neural":[13],"network":[14],"optimization,":[15],"and":[16,42,84,106,134,147,154,179],"also":[18],"widely":[19],"adopted":[20],"federated":[22,160],"learning":[23],"(FL)":[24],"prevent":[26],"overfitting":[27,58],"local":[29,82],"clients.":[30],"In":[31],"this":[32,90],"paper,":[33],"we":[34,92,121],"first":[35],"explore":[36],"the":[37,50,70,123,132,188,197,201,205,212],"choices":[38],"of":[39,52,125,131,143,190,214],"weight":[40,45,61,135,202],"identify":[43],"that":[44,110,168],"value":[47],"appreciably":[48],"influences":[49],"convergence":[51,145,178],"existing":[53,117,172],"FL":[54,78,118,173,216],"algorithms.":[55,119,162],"While":[56],"preventing":[57],"crucial,":[60],"can":[63,111],"introduce":[64],"different":[66,158],"optimization":[67,96,161],"goal":[68],"towards":[69],"global":[71],"objective,":[72],"which":[73],"further":[75],"amplified":[76],"due":[79],"multiple":[81],"updates":[83],"heterogeneous":[85],"data":[86],"distribution.":[87],"To":[88],"address":[89],"challenge,":[91],"develop":[93],"{\\it":[94],"Federated":[95],"with":[97,157],"Normalized":[98],"Annealing":[99],"Regularization}":[100],"(FedNAR),":[101],"simple":[103],"yet":[104],"effective":[105],"versatile":[107],"algorithmic":[108],"plug-in":[109],"be":[112],"seamlessly":[113],"integrated":[114],"into":[115,171],"any":[116],"Essentially,":[120],"regulate":[122],"magnitude":[124],"each":[126],"update":[127],"by":[128],"performing":[129],"co-clipping":[130],"gradient":[133],"decay.":[136],"We":[137],"provide":[138],"comprehensive":[140],"theoretical":[141],"analysis":[142],"FedNAR's":[144],"rate":[146],"conduct":[148],"extensive":[149],"experiments":[150],"on":[151],"both":[152],"vision":[153],"language":[155],"datasets":[156],"backbone":[159],"Our":[163,221],"experimental":[164],"results":[165],"consistently":[166],"demonstrate":[167],"incorporating":[169],"FedNAR":[170,184,195],"algorithms":[174,217],"leads":[175],"accelerated":[177],"heightened":[180],"model":[181],"accuracy.":[182],"Moreover,":[183],"exhibits":[185],"resilience":[186],"face":[189],"various":[191],"hyperparameter":[192],"configurations.":[193],"Specifically,":[194],"has":[196],"ability":[198],"self-adjust":[200],"when":[204],"initial":[206],"specification":[207],"not":[209],"optimal,":[210],"while":[211],"accuracy":[213],"traditional":[215],"would":[218],"markedly":[219],"decline.":[220],"codes":[222],"are":[223],"released":[224],"at":[225],"\\href{https://github.com/ljb121002/fednar}{https://github.com/ljb121002/fednar}.":[226]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}