{"id":"https://openalex.org/W7163898681","doi":"https://doi.org/10.48550/arxiv.2606.06764","title":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","display_name":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163898681","doi":"https://doi.org/10.48550/arxiv.2606.06764"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06764","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.06764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138116032","display_name":"Junyu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Junyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138167327","display_name":"Puyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Puyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046468616","display_name":"Yunwen Lei","orcid":"https://orcid.org/0000-0002-5383-467X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Yunwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048960543","display_name":"Yiming Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138150721","display_name":"Ding-Xuan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Ding-Xuan","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":false,"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":0.9692000150680542,"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":0.9692000150680542,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.008200000040233135,"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/T12676","display_name":"Machine Learning and ELM","score":0.006000000052154064,"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8039000034332275},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7954999804496765},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.7656000256538391},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6818000078201294},{"id":"https://openalex.org/keywords/tangent","display_name":"Tangent","score":0.49790000915527344},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4309000074863434},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4124000072479248}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8039000034332275},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7954999804496765},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7656000256538391},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6818000078201294},{"id":"https://openalex.org/C138187205","wikidata":"https://www.wikidata.org/wiki/Q131251","display_name":"Tangent","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48559999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47769999504089355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.424699991941452},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.39809998869895935},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28360000252723694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06764","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06764","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,"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"},"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":{"Recent":[0],"progress":[1],"has":[2],"been":[3],"made":[4],"in":[5,45],"understanding":[6],"the":[7,20,29,46,80,99,102,110],"statistical":[8],"generalization":[9,61,134],"performance":[10],"of":[11,28,48,85],"gradient":[12,69,74,124],"descent":[13,70,75,125],"methods":[14,126],"for":[15,63,89,127],"overparameterized":[16],"neural":[17,21,50],"networks":[18,66,130],"within":[19],"tangent":[22],"kernel":[23,139],"(NTK)":[24],"regime.":[25],"However,":[26],"most":[27],"existing":[30],"work":[31],"on":[32,136],"regression":[33],"problems":[34],"is":[35],"limited":[36],"to":[37,109],"shallow":[38],"network":[39,103,111],"architectures,":[40],"leaving":[41],"a":[42,59],"notable":[43],"gap":[44,56],"theory":[47],"deep":[49,64,95,128],"networks.":[51],"This":[52],"paper":[53],"addresses":[54],"this":[55],"by":[57],"presenting":[58],"comprehensive":[60],"analysis":[62],"ReLU":[65,96,129],"trained":[67],"using":[68],"(GD)":[71],"and":[72,92,113],"stochastic":[73],"(SGD).":[76],"Specifically,":[77],"we":[78],"establish":[79],"first":[81],"known":[82],"minimax-optimal":[83],"rates":[84,135],"excess":[86],"population":[87],"risk":[88],"both":[90],"GD":[91],"SGD":[93],"with":[94,107,121,138],"networks,":[97],"under":[98],"assumption":[100],"that":[101,120],"width":[104],"scales":[105],"polynomially":[106],"respect":[108],"depth":[112],"training":[114],"sample":[115],"size.":[116],"Our":[117],"results":[118],"demonstrate":[119],"sufficient":[122],"width,":[123],"can":[131],"achieve":[132],"optimal":[133],"par":[137],"methods.":[140]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-09T00:00:00"}