{"id":"https://openalex.org/W7223016097","doi":"https://doi.org/10.48550/arxiv.2610.24538","title":"Accelerating Finite-Sum Bilevel Optimization with Fully First-Order Oracles","display_name":"Accelerating Finite-Sum Bilevel Optimization with Fully First-Order Oracles","publication_year":2026,"publication_date":"2026-10-17","ids":{"openalex":"https://openalex.org/W7223016097","doi":"https://doi.org/10.48550/arxiv.2610.24538"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.24538","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.24538","pdf_url":"https://arxiv.org/pdf/2610.24538","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/2610.24538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110973488","display_name":"Qihao Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Qihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5159136830","display_name":"Shanshui Niu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Shanshui","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":true,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0008999999845400453,"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":0.00019999999494757503,"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/bi-level-optimization","display_name":"bi-level optimization","score":0.9919999837875366},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"variance reduction","score":0.7170000076293945},{"id":"https://openalex.org/keywords/complexity-bounds","display_name":"complexity bounds","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6636999845504761},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6606000065803528},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.6111999750137329},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5722000002861023},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C115527620","wikidata":"https://www.wikidata.org/wiki/Q769909","display_name":"Nonlinear programming","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.31029999256134033},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.24538","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.24538","pdf_url":"https://arxiv.org/pdf/2610.24538","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.2610.24538","doi":"https://doi.org/10.48550/arxiv.2610.24538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.24538","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:2610.24538","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.24538","pdf_url":"https://arxiv.org/pdf/2610.24538","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":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223016097.pdf","grobid_xml":"https://content.openalex.org/works/W7223016097.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2787415863","https://openalex.org/W4416944554","https://openalex.org/W7206168535"],"related_works":["https://openalex.org/W4382334315","https://openalex.org/W4416776667","https://openalex.org/W4386557162","https://openalex.org/W2606904667","https://openalex.org/W7220909258","https://openalex.org/W7213919814","https://openalex.org/W4396653224","https://openalex.org/W7165370537","https://openalex.org/W7215074586","https://openalex.org/W3126652544"],"abstract_inverted_index":{"We":[0,12],"study":[1],"nonconvex--strongly-convex":[2],"bilevel":[3],"optimization":[4],"with":[5,26,104],"finite-sum":[6,69],"objectives":[7],"and":[8,57,74,118],"fully":[9,80],"first-order":[10,81],"oracles.":[11],"propose":[13],"Sampled":[14],"Implicit":[15],"Corrections":[16],"for":[17,29,84,94,126],"Bilevel":[18],"Optimization":[19],"(SICBO),":[20],"which":[21,98],"combines":[22],"a":[23,40,91],"penalty":[24],"approximation":[25],"variance-reduced":[27],"corrections":[28],"the":[30,52,60,76,114],"lower-level":[31,62],"variables.":[32],"Under":[33],"componentwise":[34],"lower":[35],"strong":[36],"convexity,":[37],"SICBO":[38],"finds":[39],"point":[41],"$x$":[42],"satisfying":[43],"$\\mathbb{E}\\|\\nabla\u03a6(x)\\|^2\\le\\varepsilon^2$":[44],"within":[45],"$\\tilde{O}(N+\\sqrt{N}\u03ba^{7/2}\\varepsilon^{-2})$":[46],"component-gradient":[47],"calls,":[48],"where":[49],"$N$":[50,117],"is":[51,59,120],"total":[53],"number":[54],"of":[55,101,106],"components":[56],"$\u03ba$":[58],"normalized":[61],"condition":[63],"number.":[64],"The":[65],"bound":[66,93],"achieves":[67],"square-root":[68],"dependence":[70,115],"using":[71],"only":[72],"gradients":[73],"preserves":[75],"best":[77],"known":[78],"deterministic":[79],"condition-number":[82],"exponent":[83],"smooth":[85],"problems.":[86],"Our":[87],"improvement":[88],"follows":[89],"from":[90],"curvature-dependent":[92],"nonlinear":[95],"correction":[96],"errors,":[97],"permits":[99],"epochs":[100],"length":[102],"$\\tilde\u0398(\\sqrt{N/\u03ba})$":[103],"batches":[105],"size":[107],"$\\tilde\u0398(\\sqrt{N\u03ba})$.":[108],"A":[109],"single-level":[110],"reduction":[111],"shows":[112],"that":[113],"on":[116],"$\\varepsilon$":[119],"optimal":[121],"up":[122],"to":[123],"logarithmic":[124],"factors":[125],"fixed":[127],"$\u03ba$.":[128]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-21T00:00:00"}