{"id":"https://openalex.org/W4302013045","doi":"https://doi.org/10.48550/arxiv.2210.01063","title":"On Stability and Generalization of Bilevel Optimization Problem","display_name":"On Stability and Generalization of Bilevel Optimization Problem","publication_year":2022,"publication_date":"2022-10-03","ids":{"openalex":"https://openalex.org/W4302013045","doi":"https://doi.org/10.48550/arxiv.2210.01063"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.01063","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01063","pdf_url":"https://arxiv.org/pdf/2210.01063","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/2210.01063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101627226","display_name":"Meng Ding","orcid":"https://orcid.org/0000-0002-2913-1712","observed_orcids":["https://orcid.org/0000-0002-2913-1712"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015623737","display_name":"Mingxi Lei","orcid":"https://orcid.org/0000-0003-0679-4203","observed_orcids":["https://orcid.org/0000-0003-0679-4203"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei, Mingxi","raw_affiliation_strings":["Department of Computer Science and Engineering The State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering The State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046468616","display_name":"Yunwen Lei","orcid":"https://orcid.org/0000-0002-5383-467X","observed_orcids":["https://orcid.org/0000-0002-5383-467X"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lei, Yunwen","raw_affiliation_strings":["School of Computer Science University of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of Birmingham","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401482","display_name":"Di Wang","orcid":"https://orcid.org/0000-0003-4908-0243","observed_orcids":["https://orcid.org/0000-0003-4908-0243","https://orcid.org/0009-0001-5741-6694"]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Wang, Di","raw_affiliation_strings":["Division of CEMSE King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of CEMSE King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188376","display_name":"Jinhui Xu","orcid":"https://orcid.org/0009-0009-7414-3411","observed_orcids":["https://orcid.org/0009-0009-7414-3411"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Jinhui","raw_affiliation_strings":["Department of Computer Science and Engineering The State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering The State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/bi-level-optimization","display_name":"bi-level optimization","score":0.9869999885559082},{"id":"https://openalex.org/keywords/generalization-bounds","display_name":"generalization bounds","score":0.8330000042915344},{"id":"https://openalex.org/keywords/algorithmic-stability","display_name":"algorithm stability","score":0.9950000047683716},{"id":"https://openalex.org/keywords/gradient-based-optimization","display_name":"gradient-based optimization","score":0.6259999871253967},{"id":"https://openalex.org/keywords/first-order-methods","display_name":"first-order methods","score":0.628000020980835},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.6259999871253967},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.921999990940094}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8606292605400085},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.8416131138801575},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6701474189758301},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.5685727596282959},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5617149472236633},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5086615681648254},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5075279474258423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4780186414718628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4775139391422272},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.46470585465431213},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.4538986086845398},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14875730872154236},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.01063","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01063","pdf_url":"https://arxiv.org/pdf/2210.01063","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.2210.01063","doi":"https://doi.org/10.48550/arxiv.2210.01063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.01063","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.01063","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01063","pdf_url":"https://arxiv.org/pdf/2210.01063","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4302013045.pdf","grobid_xml":"https://content.openalex.org/works/W4302013045.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2597452529","https://openalex.org/W2786022758","https://openalex.org/W2787415863","https://openalex.org/W2803895400","https://openalex.org/W3080894165","https://openalex.org/W3081918527","https://openalex.org/W3157449124","https://openalex.org/W4287330080","https://openalex.org/W4317897806","https://openalex.org/W4387601958"],"related_works":["https://openalex.org/W7155374158","https://openalex.org/W4401024414","https://openalex.org/W3171006812","https://openalex.org/W3092809425","https://openalex.org/W3112047150","https://openalex.org/W3127438322","https://openalex.org/W4287330080","https://openalex.org/W3193127553","https://openalex.org/W3167655307","https://openalex.org/W4323651112"],"abstract_inverted_index":{"(Stochastic)":[0],"bilevel":[1,72],"optimization":[2,73],"is":[3,110,184],"a":[4,12,60,78,92,178],"frequently":[5],"encountered":[6,186],"problem":[7,32],"in":[8,87,154,187],"machine":[9],"learning":[10],"with":[11],"wide":[13],"range":[14],"of":[15,26,66],"applications":[16],"such":[17,158],"as":[18,159],"meta-learning,":[19],"hyper-parameter":[20,209],"optimization,":[21],"and":[22,84,90,128,164,195,208],"reinforcement":[23],"learning.":[24],"Most":[25],"the":[27,37,41,64,71,99,111,117,122,142,170,201],"existing":[28,138],"studies":[29],"on":[30,35,63,206],"this":[31,56],"only":[33,141],"focused":[34],"analyzing":[36],"convergence":[38,42],"or":[39],"improving":[40],"rate,":[43],"while":[44,137],"little":[45],"effort":[46],"has":[47],"been":[48],"devoted":[49],"to":[50,105,134,146,177],"understanding":[51],"its":[52],"generalization":[53,65,85,95,202],"behaviors.":[54],"In":[55],"paper,":[57],"we":[58,190],"conduct":[59],"thorough":[61],"analysis":[62,150,168,194],"first-order":[67],"(gradient-based)":[68],"methods":[69],"for":[70,121,169],"problem.":[74],"We":[75,114],"first":[76,118],"establish":[77],"fundamental":[79],"connection":[80],"between":[81],"algorithmic":[82],"stability":[83,119],"error":[86,203],"different":[88],"forms":[89],"give":[91],"high":[93],"probability":[94],"bound":[96],"which":[97],"improves":[98],"previous":[100],"best":[101],"one":[102],"from":[103],"$\\bigO(\\sqrt{n})$":[104],"$\\bigO(\\log":[106],"n)$,":[107],"where":[108,125],"$n$":[109],"sample":[112],"size.":[113],"then":[115],"provide":[116],"bounds":[120],"general":[123],"case":[124],"both":[126],"inner":[127],"outer":[129,143],"level":[130,144],"parameters":[131],"are":[132],"subject":[133],"continuous":[135],"update,":[136],"work":[139],"allows":[140],"parameter":[145],"be":[147,152,175],"updated.":[148],"Our":[149,167],"can":[151,173,199],"applied":[153],"various":[155],"standard":[156],"settings":[157],"strongly-convex-strongly-convex":[160],"(SC-SC),":[161],"convex-convex":[162],"(C-C),":[163],"nonconvex-nonconvex":[165],"(NC-NC).":[166],"NC-NC":[171],"setting":[172,182],"also":[174],"extended":[176],"particular":[179],"nonconvex-strongly-convex":[180],"(NC-SC)":[181],"that":[183],"commonly":[185],"practice.":[188],"Finally,":[189],"corroborate":[191],"our":[192],"theoretical":[193],"demonstrate":[196],"how":[197],"iterations":[198],"affect":[200],"by":[204],"experiments":[205],"meta-learning":[207],"optimization.":[210]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-10-06T00:00:00"}