{"id":"https://openalex.org/W4401023915","doi":"https://doi.org/10.24963/ijcai.2024/508","title":"Provable Acceleration of Nesterov\u2019s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks","display_name":"Provable Acceleration of Nesterov\u2019s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401023915","doi":"https://doi.org/10.24963/ijcai.2024/508"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2024/508","doi":"https://doi.org/10.24963/ijcai.2024/508","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/508","pdf_url":"https://www.ijcai.org/proceedings/2024/0508.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2024/0508.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xin Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Tao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tao","raw_affiliation_strings":["Strategic Assessments and Consultation Institute, Academy of Military Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Strategic Assessments and Consultation Institute, Academy of Military Science","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014299271","display_name":"Dazhi Zhan","orcid":"https://orcid.org/0000-0003-2766-3405","observed_orcids":["https://orcid.org/0000-0003-2766-3405"]},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dazhi Zhan","raw_affiliation_strings":["Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037669752","display_name":"Zhisong Pan","orcid":"https://orcid.org/0000-0001-8615-7313","observed_orcids":["https://orcid.org/0000-0001-8615-7313","https://orcid.org/0009-0001-6683-699X"]},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisong Pan","raw_affiliation_strings":["Army Engineering University of PLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3054,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50447172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4596","last_page":"4604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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":1.0,"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/T10320","display_name":"Neural Networks and Applications","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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.0,"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/nesterov-s-accelerated-gradient","display_name":"Nesterov's accelerated gradient","score":0.9679999947547913},{"id":"https://openalex.org/keywords/heavy-ball-method","display_name":"heavy ball method","score":0.9940000176429749},{"id":"https://openalex.org/keywords/momentum-method","display_name":"momentum methods","score":0.7680000066757202},{"id":"https://openalex.org/keywords/overparameterized-neural-networks","display_name":"overparameterized neural networks","score":0.9340000152587891},{"id":"https://openalex.org/keywords/neural-tangent-kernel","display_name":"neural tangent kernel","score":0.7350000143051147},{"id":"https://openalex.org/keywords/convergence-rate-bounds","display_name":"convergence rate bounds","score":0.7099999785423279},{"id":"https://openalex.org/keywords/random-initialization","display_name":"random initialization","score":0.7549999952316284},{"id":"https://openalex.org/keywords/first-order-methods","display_name":"first-order methods","score":0.640999972820282},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7797549962997437},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.6700141429901123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593207716941833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.646155834197998},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5884020924568176},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5182916522026062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131168961524963},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4184170365333557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2663941979408264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1992562711238861},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07669517397880554},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07265681028366089},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2024/508","doi":"https://doi.org/10.24963/ijcai.2024/508","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/508","pdf_url":"https://www.ijcai.org/proceedings/2024/0508.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.03941","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.03941","pdf_url":"https://arxiv.org/pdf/2208.03941","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.2208.03941","doi":"https://doi.org/10.48550/arxiv.2208.03941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.03941","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":"doi:10.24963/ijcai.2024/508","doi":"https://doi.org/10.24963/ijcai.2024/508","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/508","pdf_url":"https://www.ijcai.org/proceedings/2024/0508.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3367274174","display_name":null,"funder_award_id":"62106281","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4683421875","display_name":null,"funder_award_id":"62076251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401023915.pdf","grobid_xml":"https://content.openalex.org/works/W4401023915.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2750384547","https://openalex.org/W2948046738","https://openalex.org/W2987473824","https://openalex.org/W3133133298","https://openalex.org/W4401051688"],"related_works":["https://openalex.org/W4283069798","https://openalex.org/W3179599150","https://openalex.org/W4224273755","https://openalex.org/W3094346332","https://openalex.org/W3090423162","https://openalex.org/W4393282664","https://openalex.org/W4380990802","https://openalex.org/W2947461788","https://openalex.org/W2975217196","https://openalex.org/W2917744435"],"abstract_inverted_index":{"Due":[0],"to":[1,83,101],"its":[2],"simplicity":[3],"and":[4,69,127,134,155],"efficiency,":[5],"the":[6,19,23,33,49,64,76,116,120,149,160,165],"first-order":[7,34,79],"gradient":[8,72,80],"method":[9,35,68],"has":[10,30],"been":[11],"extensively":[12],"employed":[13],"in":[14,106,171],"training":[15,44,59,107,117,172],"neural":[16,24,46,108,123,135,173],"networks.":[17,109,174],"Although":[18],"optimization":[20],"problem":[21,118],"of":[22,38,51,58,78,119,148,167],"network":[25,124],"is":[26,36,53],"non-convex,":[27],"recent":[28],"research":[29],"proved":[31],"that":[32,57],"capable":[37],"attaining":[39],"a":[40],"global":[41],"minimum":[42],"during":[43],"over-parameterized":[45],"networks,":[47],"where":[48],"number":[50],"parameters":[52],"significantly":[54],"larger":[55],"than":[56,94],"instances.":[60],"Momentum":[61],"methods,":[62],"including":[63],"heavy":[65],"ball":[66],"(HB)":[67],"Nesterov's":[70],"accelerated":[71,85],"(NAG)":[73],"method,":[74],"are":[75],"workhorse":[77],"methods":[81],"owning":[82],"their":[84,103],"convergence.":[86],"In":[87],"practice,":[88],"NAG":[89,168],"often":[90],"exhibits":[91],"superior":[92],"performance":[93],"HB.":[95],"However,":[96],"current":[97],"theoretical":[98,162,179],"works":[99],"fail":[100],"distinguish":[102],"convergence":[104,150],"difference":[105],"To":[110],"fill":[111],"this":[112],"gap,":[113],"we":[114,176],"consider":[115],"two-layer":[121],"ReLU":[122],"under":[125],"over-parameterization":[126],"random":[128],"initialization.":[129],"Leveraging":[130],"high-resolution":[131],"dynamical":[132],"systems":[133],"tangent":[136],"kernel":[137],"(NTK)":[138],"theory,":[139],"our":[140,178],"result":[141],"not":[142],"only":[143],"establishes":[144],"tighter":[145],"upper":[146],"bounds":[147],"rate":[151],"for":[152,164],"both":[153],"HB":[154,170],"NAG,":[156],"but":[157],"also":[158],"provides":[159],"first":[161],"guarantee":[163],"acceleration":[166],"over":[169],"Finally,":[175],"validate":[177],"results":[180],"on":[181],"three":[182],"benchmark":[183],"datasets.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-07-27T00:00:00"}