{"id":"https://openalex.org/W4414359539","doi":"https://doi.org/10.24963/ijcai.2025/784","title":"Federated Stochastic Bilevel Optimization with Fully First-Order Gradients","display_name":"Federated Stochastic Bilevel Optimization with Fully First-Order Gradients","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359539","doi":"https://doi.org/10.24963/ijcai.2025/784"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/784","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"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"]},{"id":"https://openalex.org/I2801004183","display_name":"Temple College","ror":"https://ror.org/038s1ax16","country_code":"US","type":"education","lineage":["https://openalex.org/I2801004183"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yihan Zhang","raw_affiliation_strings":["Temple University"],"affiliations":[{"raw_affiliation_string":"Temple University","institution_ids":["https://openalex.org/I2801004183","https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119679351","display_name":"Rohit Dhaipule","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Dhaipule","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102829972","display_name":"Chiu C. Tan","orcid":"https://orcid.org/0000-0002-5758-6394"},"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"]},{"id":"https://openalex.org/I2801004183","display_name":"Temple College","ror":"https://ror.org/038s1ax16","country_code":"US","type":"education","lineage":["https://openalex.org/I2801004183"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chiu C. Tan","raw_affiliation_strings":["Temple University"],"affiliations":[{"raw_affiliation_string":"Temple University","institution_ids":["https://openalex.org/I2801004183","https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061469520","display_name":"Haibin Ling","orcid":"https://orcid.org/0000-0003-4094-8413"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haibin Ling","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014924409","display_name":"Hongchang Gao","orcid":"https://orcid.org/0000-0003-3462-1879"},"institutions":[{"id":"https://openalex.org/I2801004183","display_name":"Temple College","ror":"https://ror.org/038s1ax16","country_code":"US","type":"education","lineage":["https://openalex.org/I2801004183"]},{"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":"Hongchang Gao","raw_affiliation_strings":["Temple University"],"affiliations":[{"raw_affiliation_string":"Temple University","institution_ids":["https://openalex.org/I2801004183","https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100350077"],"corresponding_institution_ids":["https://openalex.org/I2801004183","https://openalex.org/I84392919"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34120879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7047","last_page":"7055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.972000002861023,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.965499997138977,"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/bilevel-optimization","display_name":"Bilevel optimization","score":0.8169000148773193},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.801800012588501},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.6460999846458435},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6111999750137329},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.5532000064849854},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5149999856948853},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4803999960422516},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.8169000148773193},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.801800012588501},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6926000118255615},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.6460999846458435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6439999938011169},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4803999960422516},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.44999998807907104},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4438999891281128},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C116149140","wikidata":"https://www.wikidata.org/wiki/Q2070951","display_name":"Descent direction","level":4,"score":0.3133000135421753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30000001192092896},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2526000142097473},{"id":"https://openalex.org/C133512626","wikidata":"https://www.wikidata.org/wiki/Q787371","display_name":"Automatic differentiation","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/784","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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],"stochastic":[1,23,53],"bilevel":[2,24,55],"optimization":[3,25],"has":[4],"been":[5],"actively":[6],"studied":[7],"in":[8,16,42],"recent":[9],"years":[10],"due":[11],"to":[12,38,97,110],"its":[13],"widespread":[14],"applications":[15],"machine":[17],"learning.":[18],"However,":[19],"most":[20],"existing":[21],"federated":[22,52],"algorithms":[26],"require":[27,70],"the":[28,71,99,112,119,124],"computation":[29,72],"of":[30,73,101,115,126],"second-order":[31,74],"Hessian":[32,75],"and":[33,76],"Jacobian":[34,77],"matrices,":[35,78],"which":[36],"leads":[37],"longer":[39],"running":[40,81],"times":[41],"practice.":[43],"To":[44],"address":[45],"these":[46],"challenges,":[47],"we":[48,84],"propose":[49],"a":[50,86,92,107],"novel":[51,87],"variance-reduced":[54],"gradient":[56],"descent":[57],"algorithm":[58],"that":[59],"relies":[60],"solely":[61],"on":[62],"first-order":[63],"oracles.":[64],"Specifically,":[65],"our":[66,116,127],"approach":[67],"does":[68],"not":[69],"significantly":[79],"reducing":[80],"time.":[82],"Furthermore,":[83],"introduce":[85],"learning":[88,95],"rate":[89,114],"mechanism,":[90],"i.e.,":[91],"constant":[93],"single-time-scale":[94],"rate,":[96],"coordinate":[98],"update":[100],"different":[102],"variables.":[103],"We":[104],"also":[105],"present":[106],"new":[108],"strategy":[109],"establish":[111],"convergence":[113],"algorithm.":[117,129],"Finally,":[118],"extensive":[120],"experimental":[121],"results":[122],"confirm":[123],"efficacy":[125],"proposed":[128]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}