{"id":"https://openalex.org/W7154991079","doi":"https://doi.org/10.1007/s10994-026-07040-y","title":"On the Communication Complexity of Decentralized Stochastic Bilevel Optimization","display_name":"On the Communication Complexity of Decentralized Stochastic Bilevel Optimization","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7154991079","doi":"https://doi.org/10.1007/s10994-026-07040-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-026-07040-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07040-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07040-y.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07040-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100350077","display_name":"Yihan Zhang","orcid":"https://orcid.org/0000-0002-6465-6258"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yihan Zhang","raw_affiliation_strings":["Department of Computer and Information Sciences, Temple University, 1925 N. 12th Street, Philadelphia, 19122, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Temple University, 1925 N. 12th Street, Philadelphia, 19122, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122967481","display_name":"My T. Thai","orcid":null},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"My T. Thai","raw_affiliation_strings":["Department of Computer and Information Science and Engineering, University of Florida, 1889 Museum Road, Gainesville, 32611, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science and Engineering, University of Florida, 1889 Museum Road, Gainesville, 32611, FL, USA","institution_ids":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134011160","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-3472-1717"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["Department of Computer and Information Sciences, Temple University, 1925 N. 12th Street, Philadelphia, 19122, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Temple University, 1925 N. 12th Street, Philadelphia, 19122, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134012471","display_name":"Hongchang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongchang Gao","raw_affiliation_strings":["Department of Computer and Information Sciences, Temple University, 1925 N. 12th Street, Philadelphia, 19122, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Temple University, 1925 N. 12th Street, Philadelphia, 19122, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5134012471"],"corresponding_institution_ids":["https://openalex.org/I84392919"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4377691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"115","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9721999764442444,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9721999764442444,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.007499999832361937,"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":0.003000000026077032,"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":0.6901999711990356},{"id":"https://openalex.org/keywords/bilevel-optimization","display_name":"Bilevel optimization","score":0.677299976348877},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6054999828338623},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5396999716758728},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5078999996185303},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.48539999127388},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.47040000557899475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732699990272522},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6901999711990356},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.677299976348877},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6556000113487244},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5078999996185303},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.47040000557899475},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.27810001373291016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-026-07040-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07040-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07040-y.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-026-07040-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07040-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07040-y.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2632239271","display_name":"CAREER: Decentralized Federated Compositional Learning: Algorithm and Theory","funder_award_id":"2339545","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7931996158","display_name":"Collaborative Research: III: Small: Foundations for Trustworthy Decentralized Federated Learning","funder_award_id":"2416607","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8424121293","display_name":"Collaborative Research: CNS Core: Medium: Data Augmentation and Adaptive Learning for Next Generation Wireless Spectrum Systems","funder_award_id":"2107014","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7154991079.pdf","grobid_xml":"https://content.openalex.org/works/W7154991079.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4200629126","https://openalex.org/W4211116959","https://openalex.org/W4224932938","https://openalex.org/W4297882636","https://openalex.org/W4393161220","https://openalex.org/W7133224171"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Stochastic":[1],"bilevel":[2,21,29,67],"optimization":[3,22,30],"finds":[4],"widespread":[5],"applications":[6],"in":[7,48,149],"machine":[8],"learning,":[9],"including":[10],"meta-learning,":[11],"hyperparameter":[12],"optimization,":[13],"and":[14,44,74,85,114],"neural":[15],"architecture":[16],"search.":[17],"To":[18,57,128],"extend":[19],"stochastic":[20,28,66],"to":[23,54,157],"distributed":[24],"data,":[25],"several":[26],"decentralized":[27,65],"algorithms":[31,70,79],"have":[32,143],"been":[33,144],"developed.":[34],"However,":[35],"existing":[36,90],"methods":[37],"often":[38],"suffer":[39],"from":[40],"slow":[41],"convergence":[42,83,94,126,160],"rates":[43,84],"high":[45],"communication":[46,87,115],"costs":[47,88],"heterogeneous":[49,122,151],"settings,":[50],"limiting":[51],"their":[52],"applicability":[53],"real-world":[55],"tasks.":[56],"address":[58],"these":[59],"issues,":[60],"we":[61,154],"propose":[62],"two":[63],"novel":[64],"gradient":[68],"descent":[69],"based":[71],"on":[72,99],"simultaneous":[73],"alternating":[75,164],"update":[76,165],"strategies.":[77],"Our":[78],"can":[80],"achieve":[81],"faster":[82],"lower":[86],"than":[89],"methods.":[91],"Importantly,":[92],"our":[93,106,132,180],"analyses":[95,108],"do":[96],"not":[97],"rely":[98],"strong":[100],"assumptions":[101,148],"regarding":[102,116],"heterogeneity.":[103],"More":[104],"importantly,":[105],"theoretical":[107,141],"clearly":[109],"disclose":[110],"how":[111,156],"the":[112,117,121,125,129,136,150,159,163,170,177],"computation":[113],"Hessian-inverse-vector":[118],"product":[119],"under":[120],"setting":[123],"affects":[124],"rate.":[127],"best":[130],"of":[131,179],"knowledge,":[133],"this":[134],"is":[135],"first":[137],"time":[138],"such":[139],"favorable":[140],"results":[142,175],"achieved":[145],"with":[146,169],"mild":[147],"setting.":[152],"Furthermore,":[153],"demonstrate":[155],"establish":[158],"rate":[161],"for":[162],"strategy":[166],"when":[167],"combined":[168],"variance-reduced":[171],"gradient.":[172],"Finally,":[173],"experimental":[174],"confirm":[176],"efficacy":[178],"algorithms.":[181]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2026-04-21T00:00:00"}