{"id":"https://openalex.org/W7216470962","doi":"https://doi.org/10.48550/arxiv.2610.01843","title":"Optimal Stochastic Bilevel Optimization with First-Order Oracles","display_name":"Optimal Stochastic Bilevel Optimization with First-Order Oracles","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7216470962","doi":"https://doi.org/10.48550/arxiv.2610.01843"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01843","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01843","pdf_url":"https://arxiv.org/pdf/2610.01843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.01843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015686368","display_name":"Linxuan Pan","orcid":"https://orcid.org/0009-0008-8775-9066","observed_orcids":["https://orcid.org/0009-0008-8775-9066"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Linxuan","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5155561391","display_name":"Junchi Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Junchi","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.98580002784729,"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":0.98580002784729,"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/T10545","display_name":"Optimization and Variational Analysis","score":0.007199999876320362,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-bilevel-optimization","display_name":"stochastic bilevel optimization","score":0.8880000114440918},{"id":"https://openalex.org/keywords/finite-differences","display_name":"finite differences","score":0.6140000224113464},{"id":"https://openalex.org/keywords/implicit-differentiation","display_name":"implicit differentiation","score":0.8149999976158142},{"id":"https://openalex.org/keywords/critical-points","display_name":"critical points","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6287000179290771},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6039000153541565},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.5748000144958496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5555999875068665},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3368000090122223},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2987642246","wikidata":"https://www.wikidata.org/wiki/Q5452196","display_name":"First order","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C85522705","wikidata":"https://www.wikidata.org/wiki/Q3278015","display_name":"Line search","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C111771559","wikidata":"https://www.wikidata.org/wiki/Q66295","display_name":"Derivative (finance)","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01843","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01843","pdf_url":"https://arxiv.org/pdf/2610.01843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.01843","doi":"https://doi.org/10.48550/arxiv.2610.01843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01843","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.01843","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01843","pdf_url":"https://arxiv.org/pdf/2610.01843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216470962.pdf","grobid_xml":"https://content.openalex.org/works/W7216470962.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2755306766","https://openalex.org/W2787415863","https://openalex.org/W2993258424","https://openalex.org/W4416944554","https://openalex.org/W4417409482","https://openalex.org/W7133206818","https://openalex.org/W7204169045"],"related_works":["https://openalex.org/W7213919814","https://openalex.org/W4382334315","https://openalex.org/W7133202369","https://openalex.org/W4416776667","https://openalex.org/W4391800790","https://openalex.org/W4318348391","https://openalex.org/W7220748465","https://openalex.org/W4417409482","https://openalex.org/W7160860326","https://openalex.org/W7212087685"],"abstract_inverted_index":{"We":[0,10,77],"study":[1],"nonconvex--strongly-convex":[2],"bilevel":[3,106],"optimization":[4],"under":[5],"a":[6,13,80,91,97,105,109,113],"stochastic":[7,74,99,136],"first-order":[8,15,137],"oracle.":[9],"introduce":[11],"MRT-FD,":[12],"single-loop":[14],"method":[16],"that":[17],"simultaneously":[18],"tracks":[19],"the":[20,23,27,35,48,64,118,130],"upper-level":[21],"variable,":[22,66],"lower-level":[24,65,115],"solution,":[25],"and":[26,46,101],"auxiliary":[28],"response":[29],"arising":[30],"from":[31,90],"implicit":[32],"differentiation":[33],"of":[34,41],"hyperobjective.":[36],"MRT-FD":[37,67],"performs":[38],"one":[39],"update":[40],"each":[42],"variable":[43],"per":[44],"iteration":[45],"approximates":[47],"second-order":[49],"derivative":[50],"actions":[51],"using":[52,72],"order-$p$":[53],"finite":[54,59,127],"differences.":[55],"For":[56],"any":[57],"fixed":[58,126],"smoothness":[60],"order":[61],"$p\\ge1$":[62],"in":[63,134],"finds":[68],"an":[69],"$\\varepsilon$-stationary":[70],"point":[71],"$\\mathcal{O}(\\varepsilon^{-4-2/p})$":[73],"gradient":[75],"queries.":[76],"also":[78],"prove":[79],"matching":[81],"$\u03a9(\\varepsilon^{-4-2/p})$":[82],"oracle":[83,138],"lower":[84],"bound.":[85],"The":[86],"lower-bound":[87],"construction":[88],"starts":[89],"hard":[92],"nonconvex":[93],"minimization":[94],"chain":[95],"with":[96,112],"stronger":[98],"oracle,":[100],"lifts":[102],"it":[103],"to":[104],"problem":[107],"through":[108],"sinusoidal":[110],"coupling":[111],"scalar":[114],"variable.":[116],"Consequently,":[117],"dependence":[119],"on":[120],"$\\varepsilon$":[121],"is":[122],"optimal":[123],"for":[124],"every":[125],"$p$,":[128],"closing":[129],"upper--lower":[131],"complexity":[132],"gap":[133],"this":[135],"setting.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}