{"id":"https://openalex.org/W7218818502","doi":"https://doi.org/10.13140/rg.2.2.11000.20480","title":"Convergence Analysis of Nesterov's Accelerated Gradient Descent under Relaxed Assumptions","display_name":"Convergence Analysis of Nesterov's Accelerated Gradient Descent under Relaxed Assumptions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7218818502","doi":"https://doi.org/10.13140/rg.2.2.11000.20480"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.33761","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33761","pdf_url":"https://arxiv.org/pdf/2610.33761","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/2610.33761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5156775264","display_name":"Chenhao Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenhao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033892491","display_name":"Junhong Lin","orcid":"https://orcid.org/0000-0002-4507-9424","observed_orcids":["https://orcid.org/0000-0002-4507-9424"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhong Lin","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":0.9663000106811523,"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":0.9663000106811523,"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":0.0142000000923872,"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"}},{"id":"https://openalex.org/T10545","display_name":"Optimization and Variational Analysis","score":0.010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8899999856948853},{"id":"https://openalex.org/keywords/smoothness-conditions","display_name":"smoothness conditions","score":0.5699999928474426},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"stochastic optimization","score":0.6650000214576721},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.9100000262260437},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"convex optimization","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.512499988079071},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5052000284194946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48260000348091125},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2937000095844269},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2610.33761","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33761","pdf_url":"https://arxiv.org/pdf/2610.33761","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.2610.33761","doi":"https://doi.org/10.48550/arxiv.2610.33761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.33761","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"},{"id":"doi:10.13140/rg.2.2.11000.20480","doi":"https://doi.org/10.13140/rg.2.2.11000.20480","is_oa":false,"landing_page_url":"https://doi.org/10.13140/rg.2.2.11000.20480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.33761","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33761","pdf_url":"https://arxiv.org/pdf/2610.33761","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":[{"id":"https://openalex.org/G5887349971","display_name":null,"funder_award_id":"12471096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6241006412","display_name":null,"funder_award_id":"2021YFA1003500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7218818502.pdf","grobid_xml":"https://content.openalex.org/works/W7218818502.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1987083649","https://openalex.org/W2024484010","https://openalex.org/W2436219157","https://openalex.org/W2963470657","https://openalex.org/W2993258424","https://openalex.org/W4407690277"],"related_works":["https://openalex.org/W3127962651","https://openalex.org/W4416398581","https://openalex.org/W3202743722","https://openalex.org/W7100389024","https://openalex.org/W7108219822","https://openalex.org/W2296276250","https://openalex.org/W7100178189","https://openalex.org/W7108202422","https://openalex.org/W1570877602","https://openalex.org/W7095913615"],"abstract_inverted_index":{"We":[0,20,37,149],"study":[1],"convergence":[2,41,85,124,153],"rates":[3,154],"of":[4,43,48,58,87,110,130,140,155],"Nesterov's":[5],"Accelerated":[6],"Gradient":[7],"Descent":[8],"(NAG)":[9],"method":[10],"for":[11,65,78],"convex":[12,68],"optimization":[13,69],"in":[14,46,70,135,159],"both":[15],"deterministic":[16],"and":[17,35,90,112,144],"stochastic":[18,79],"settings.":[19],"focus":[21],"on":[22],"a":[23],"more":[24],"general":[25],"smoothness":[26,146],"condition":[27],"raised":[28],"from":[29],"several":[30],"machine":[31],"learning":[32],"problems":[33],"empirically":[34],"theoretically.":[36],"show":[38],"the":[39,49,62,73,83,98,107,115,127,131,138,152,156,160],"accelerated":[40],"rate":[42,64,86,92,125,133],"order":[44,88,129],"$\\mathcal{O}\\left(1/T^2\\right)$":[45],"terms":[47],"function":[50],"value":[51],"gap,":[52],"given":[53],"access":[54],"to":[55,95,119],"exact":[56],"gradients":[57],"objective":[59],"functions,":[60],"matching":[61],"optimal":[63],"standard":[66],"smooth":[67],"\\citep{nesterov1983method}.":[71],"Under":[72],"relaxed":[74],"affine-variance":[75],"noise":[76,99,143],"assumption":[77],"optimization,":[80],"we":[81],"establish":[82,151],"high-probability":[84],"$\\tilde{\\mathcal{O}}\\left(\\sqrt{\\log\\left(1/\u03b4\\right)/T}\\right)$":[89],"this":[91],"could":[93],"improve":[94],"$\\tilde{\\mathcal{O}}\\left(\\log\\left(1/\u03b4\\right)/T^2\\right)$":[96],"when":[97],"parameters":[100],"are":[101,147],"sufficiently":[102],"small.":[103],"Here,":[104],"$T$":[105],"denotes":[106],"total":[108],"number":[109],"iterations":[111],"$\u03b4$":[113],"is":[114],"probability":[116],"margin.":[117],"Up":[118],"logarithm":[120],"factors,":[121],"our":[122],"probabilistic":[123],"reaches":[126],"same":[128],"expected":[132],"obtained":[134],"\\citep{ghadimi2016accelerated}":[136],"where":[137],"assumptions":[139],"bounded":[141],"variance":[142],"Lipschitz":[145],"required.":[148],"additionally":[150],"studied":[157],"algorithms":[158],"non-convex":[161],"setting.":[162]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-04T00:00:00"}