{"id":"https://openalex.org/W7165666959","doi":"https://doi.org/10.48550/arxiv.2606.22466","title":"Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm","display_name":"Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm","publication_year":2026,"publication_date":"2026-06-21","ids":{"openalex":"https://openalex.org/W7165666959","doi":"https://doi.org/10.48550/arxiv.2606.22466"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22466","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22466","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22466","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139172784","display_name":"Shengchao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Shengchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139133660","display_name":"Yongchao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yongchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8481000065803528,"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":0.8481000065803528,"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":0.07159999758005142,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.014499999582767487,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6330999732017517},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5641999840736389},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.42559999227523804},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.4092999994754791},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.40790000557899475},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.387800008058548},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.38089999556541443},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.373199999332428},{"id":"https://openalex.org/keywords/artificial-noise","display_name":"Artificial noise","score":0.37139999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987000107765198},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5641999840736389},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5047000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38510000705718994},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.38089999556541443},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.37139999866485596},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C16210155","wikidata":"https://www.wikidata.org/wiki/Q5154140","display_name":"Communication noise","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22466","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22466","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22466","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22466","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,8,53],"(FL)":[2],"is":[3,107,133],"an":[4,134],"emerging":[5],"distributed":[6],"machine":[7,52],"paradigm":[9],"that":[10],"enables":[11],"local":[12],"devices":[13],"to":[14,74,85],"jointly":[15],"train":[16],"a":[17,28,64,71,81,96,121,141],"global":[18],"model":[19],"while":[20],"keeping":[21],"data":[22,147],"decentralized":[23],"and":[24,42,57,79],"private.":[25],"We":[26],"propose":[27],"variance-reduction":[29],"based":[30],"algorithm,":[31],"VRA-FedSGD,":[32],"for":[33,101,126],"FL":[34],"in":[35,50],"the":[36,91,108,115,149],"presence":[37],"of":[38,59,99,111,124,151],"heavy-tailed":[39,76,87,112],"gradient":[40,77],"noise":[41],"communication":[43,88],"noise,":[44,78],"where":[45,105,131],"these":[46],"noises":[47],"are":[48],"prevalent":[49],"large-scale":[51],"over":[54],"wireless":[55],"networks":[56],"Internet":[58],"Things":[60],"deployments.":[61],"VRA-FedSGD":[62,94,119],"employs":[63],"momentum":[65],"variance":[66],"reduction":[67],"technique":[68],"together":[69],"with":[70,145],"nonlinear":[72],"mapping":[73],"mitigate":[75],"uses":[80],"variance-reduced":[82],"aggregation":[83],"mechanism":[84],"suppress":[86],"noise.":[89,113],"In":[90,114],"mean":[92],"sense,":[93,118],"achieves":[95,120],"convergence":[97,122],"rate":[98,123],"{\\small$\\mathcal{O}\\left(K^{-(p-1)/(2p-1)}\\right)$}":[100],"nonconvex":[102],"objective":[103,129],"functions,":[104,130],"$p$":[106],"tail":[109],"index":[110],"almost":[116],"sure":[117],"$\\tilde{\\mathcal{O}}\\left(K^{-(1-1/(p-\u03b5))}\\right)$":[125],"strongly":[127],"convex":[128],"$\u03b5$":[132],"arbitrarily":[135],"small":[136],"constant.":[137],"Simulated":[138],"experiments":[139],"on":[140],"logistic":[142],"regression":[143],"problem":[144],"real-world":[146],"verify":[148],"effectiveness":[150],"VRA-FedSGD.":[152]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}