{"id":"https://openalex.org/W7214344355","doi":"https://doi.org/10.48550/arxiv.2609.29458","title":"Precise Convergence Speed of Clipped SGD","display_name":"Precise Convergence Speed of Clipped SGD","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214344355","doi":"https://doi.org/10.48550/arxiv.2609.29458"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29458","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29458","pdf_url":"https://arxiv.org/pdf/2609.29458","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/2609.29458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066102441","display_name":"David A. R. Robin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210137929","display_name":"Lamsade","ror":"https://ror.org/03pnp1a74","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I4210137929","https://openalex.org/I4210159245","https://openalex.org/I56435720"]},{"id":"https://openalex.org/I56435720","display_name":"Universit\u00e9 Paris Dauphine-PSL","ror":"https://ror.org/052bz7812","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I56435720"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Robin, David A. R.","raw_affiliation_strings":["LAMSADE , Universit\u00e9 Paris-Dauphine , PSL Research University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LAMSADE , Universit\u00e9 Paris-Dauphine , PSL Research University","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I4210137929","https://openalex.org/I56435720"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066102441"],"corresponding_institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I4210137929","https://openalex.org/I56435720"],"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/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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.593999981880188},{"id":"https://openalex.org/keywords/l2-projection","display_name":"L2 projection","score":0.6759999990463257},{"id":"https://openalex.org/keywords/bias-control","display_name":"bias control","score":0.44999998807907104},{"id":"https://openalex.org/keywords/learning-rate-bounds","display_name":"learning rate bounds","score":0.5080000162124634},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.597000002861023},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7675999999046326},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.7318000197410583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6348000168800354},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.49380001425743103},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.421099990606308},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.41440001130104065},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34790000319480896},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29458","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29458","pdf_url":"https://arxiv.org/pdf/2609.29458","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.2609.29458","doi":"https://doi.org/10.48550/arxiv.2609.29458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29458","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.29458","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29458","pdf_url":"https://arxiv.org/pdf/2609.29458","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/G2169522505","display_name":"Foundations of robustness and reliability in artificial intelligence","funder_award_id":"ANR-23-PEIA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7080048889","display_name":null,"funder_award_id":"ANR-23","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214344355.pdf","grobid_xml":"https://content.openalex.org/works/W7214344355.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2994747431","https://openalex.org/W7161242767","https://openalex.org/W7196992468"],"related_works":["https://openalex.org/W4414841462","https://openalex.org/W4415036353","https://openalex.org/W7161242767","https://openalex.org/W7117708138","https://openalex.org/W7223094074","https://openalex.org/W3170783595","https://openalex.org/W4320721098","https://openalex.org/W4378588713","https://openalex.org/W3091804006","https://openalex.org/W7214746261"],"abstract_inverted_index":{"We":[0,50,86],"present":[1],"a":[2,37],"tightened":[3],"convergence":[4,89],"analysis":[5,82],"of":[6,21,36,39,46,55,83],"clipped":[7],"gradient":[8],"descent":[9],"on":[10,18],"$(L_0,":[11],"L_1)$-smooth":[12],"functions,":[13],"with":[14,112],"quantitative":[15],"constants.":[16],"Building":[17],"the":[19,33,40,53,79,88,117,125],"ideas":[20],"Koloskova":[22],"et":[23],"al":[24],"(2023),":[25],"we":[26],"refactor":[27],"several":[28],"case":[29],"disjunctions":[30],"to":[31,63,101,124],"reveal":[32],"central":[34],"role":[35],"control":[38],"bias":[41],"derived":[42],"from":[43,57,91,121],"fundamental":[44],"properties":[45],"$\\ell_2$-projection,":[47],"simplifying":[48],"proofs.":[49],"also":[51],"extend":[52],"domain":[54],"validity":[56],"$\u03b7\\leq":[58],"1":[59,65],"/":[60],"(9":[61],"\u03b2)$":[62],"$\u03b7<":[64],"/\u03b2$":[66],"where":[67],"$\u03b2=":[68],"L_0":[69],"+":[70],"c":[71],"L_1$":[72],"for":[73],"clipping":[74],"constant":[75],"$c$,":[76],"which":[77],"matches":[78],"more":[80,126],"traditional":[81],"smooth":[84],"functions.":[85],"strengthen":[87],"criterion":[90],"$\\left(":[92,102],"\\min_{t":[93],"<":[94,105],"T}":[95,106],"\\mathbb{E}[\\lVert":[96,107],"\\nabla":[97,108],"f(x_t)":[98,109],"\\rVert_2]":[99,110],"\\right)$":[100,111],"\\frac{1}{T}":[103],"\\sum_{t":[104],"matching":[113],"speed,":[114],"and":[115],"lower":[116],"final":[118],"achievable":[119],"loss":[120],"$\\mathcal{O}(\\min(\u03c3^2/c,":[122],"\u03c3))$":[123],"precise":[127],"$6":[128],"\\min(\u03c3^2":[129],"/c,":[130],"3":[131],"\u03c3)$.":[132]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-26T00:00:00"}