{"id":"https://openalex.org/W7165389152","doi":"https://doi.org/10.48550/arxiv.2606.19734","title":"Federated Bilevel Performative Prediction","display_name":"Federated Bilevel Performative Prediction","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165389152","doi":"https://doi.org/10.48550/arxiv.2606.19734"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19734","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.2606.19734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072590934","display_name":"Liangxin Qian","orcid":"https://orcid.org/0000-0002-7686-4580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Liangxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138988617","display_name":"Chang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053535368","display_name":"Xuanyu Cao","orcid":"https://orcid.org/0000-0003-0190-4362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Xuanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139006557","display_name":"Jun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138965492","display_name":"Kwok-Yan Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lam, Kwok-Yan","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":0.5224999785423279,"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":0.5224999785423279,"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":0.3280999958515167,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7907999753952026},{"id":"https://openalex.org/keywords/bilevel-optimization","display_name":"Bilevel optimization","score":0.6118000149726868},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6008999943733215},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5716999769210815},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4636000096797943},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.43790000677108765},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/performative-utterance","display_name":"Performative utterance","score":0.3864000141620636},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3817000091075897}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7907999753952026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300999760627747},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.6118000149726868},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4052000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C134141054","wikidata":"https://www.wikidata.org/wiki/Q965415","display_name":"Performative utterance","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C165136773","wikidata":"https://www.wikidata.org/wiki/Q1363179","display_name":"Single point of failure","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19734","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.2606.19734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19734","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":[{"id":"https://metadata.un.org/sdg/16","score":0.7945046424865723,"display_name":"Peace, Justice and strong institutions"}],"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],"bilevel":[1,56,77],"optimization":[2],"is":[3],"widely":[4],"used":[5],"for":[6,90],"nested":[7],"learning":[8],"problems":[9],"across":[10],"distributed":[11],"clients,":[12],"such":[13],"as":[14],"federated":[15,55,76,99,122],"hyperparameter":[16],"tuning":[17],"and":[18,22,45,63,86,93,114,141,150,157],"meta-learning":[19],"under":[20,69,82,110,128],"privacy":[21],"communication":[23],"constraints.":[24],"Most":[25],"existing":[26],"formulations":[27],"assume":[28],"fixed":[29],"client":[30,43],"data":[31,46],"distributions,":[32],"which":[33,107],"can":[34],"be":[35],"violated":[36],"by":[37],"performativity,":[38],"where":[39,59],"deployed":[40],"decisions":[41],"reshape":[42],"behavior":[44],"collection,":[47],"inducing":[48],"client-specific,":[49],"decision-dependent":[50,71],"distribution":[51],"shift.":[52],"We":[53,73,95],"study":[54],"performative":[57],"prediction,":[58],"both":[60],"upper-level":[61],"(UL)":[62],"lower-level":[64],"(LL)":[65],"objectives":[66],"are":[67,134],"evaluated":[68],"client-dependent,":[70],"distributions.":[72],"formalize":[74],"the":[75,103,146,162,166],"performatively":[78],"stable":[79],"(FBPS)":[80],"point":[81],"a":[83,111,116],"decoupled-risk":[84],"perspective":[85],"provide":[87],"sufficient":[88],"conditions":[89],"its":[91],"existence":[92],"uniqueness.":[94],"then":[96],"develop":[97],"two":[98],"methods":[100,168],"to":[101],"compute":[102],"FBPS":[104],"solution:":[105],"FBi-RRM,":[106],"converges":[108],"linearly":[109],"contraction":[112],"condition,":[113],"FBi-SGD,":[115],"communication-efficient":[117],"stochastic":[118],"method":[119],"based":[120],"on":[121,138],"hypergradient":[123],"estimation":[124],"with":[125],"convergence":[126],"guarantees":[127],"diminishing":[129],"step":[130],"sizes":[131],"when":[132],"sensitivities":[133],"sufficiently":[135],"small.":[136],"Experiments":[137],"strategic":[139,143],"regression":[140],"meta":[142],"classification":[144,159],"validate":[145],"predicted":[147],"stability":[148],"thresholds":[149],"demonstrate":[151],"improved":[152],"meta-generalization":[153],"over":[154],"non-performative":[155],"baselines,":[156],"CNN-based":[158],"further":[160],"demonstrates":[161],"practical":[163],"effectiveness":[164],"of":[165],"proposed":[167],"in":[169],"nonconvex":[170],"neural":[171],"network":[172],"settings.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-20T00:00:00"}