{"id":"https://openalex.org/W4399322119","doi":"https://doi.org/10.1007/s10107-024-02100-4","title":"Universal heavy-ball method for nonconvex optimization under H\u00f6lder continuous Hessians","display_name":"Universal heavy-ball method for nonconvex optimization under H\u00f6lder continuous Hessians","publication_year":2024,"publication_date":"2024-06-04","ids":{"openalex":"https://openalex.org/W4399322119","doi":"https://doi.org/10.1007/s10107-024-02100-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10107-024-02100-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10107-024-02100-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10107-024-02100-4.pdf","source":{"id":"https://openalex.org/S193920097","display_name":"Mathematical Programming","issn_l":"0025-5610","issn":["0025-5610","1436-4646"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematical Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10107-024-02100-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058530498","display_name":"Naoki Marumo","orcid":"https://orcid.org/0000-0002-7372-4275"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naoki Marumo","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7372-4275","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101795095","display_name":"Akiko Takeda","orcid":"https://orcid.org/0000-0002-8846-4496"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akiko Takeda","raw_affiliation_strings":["Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058530498"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.243,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61870581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"212","issue":"1-2","first_page":"147","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.9986000061035156,"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/mathematics","display_name":"Mathematics","score":0.7355785965919495},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.4967871308326721},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4058614671230316},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.38980191946029663},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.35020020604133606}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7355785965919495},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.4967871308326721},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4058614671230316},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38980191946029663},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.35020020604133606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10107-024-02100-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10107-024-02100-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10107-024-02100-4.pdf","source":{"id":"https://openalex.org/S193920097","display_name":"Mathematical Programming","issn_l":"0025-5610","issn":["0025-5610","1436-4646"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematical Programming","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10107-024-02100-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10107-024-02100-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10107-024-02100-4.pdf","source":{"id":"https://openalex.org/S193920097","display_name":"Mathematical Programming","issn_l":"0025-5610","issn":["0025-5610","1436-4646"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematical Programming","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7793096829","display_name":"Developing efficient algorithms for nonconvex non smooth optimization and its application to machine learning","funder_award_id":"19H04069","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8383818148","display_name":"Developing subspace methods for constrained optimization problems and their application to machine learning","funder_award_id":"23K28041","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399322119.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1985240368","https://openalex.org/W1988720110","https://openalex.org/W1994974865","https://openalex.org/W2000359198","https://openalex.org/W2000462146","https://openalex.org/W2007007407","https://openalex.org/W2009941369","https://openalex.org/W2026258334","https://openalex.org/W2053434217","https://openalex.org/W2070473094","https://openalex.org/W2097460613","https://openalex.org/W2119401655","https://openalex.org/W2124541940","https://openalex.org/W2124768887","https://openalex.org/W2135303118","https://openalex.org/W2137731592","https://openalex.org/W2155823647","https://openalex.org/W2156005216","https://openalex.org/W2398500126","https://openalex.org/W2546420264","https://openalex.org/W2599851351","https://openalex.org/W2609037894","https://openalex.org/W2763081248","https://openalex.org/W2792215433","https://openalex.org/W2901838001","https://openalex.org/W2963075511","https://openalex.org/W2963843970","https://openalex.org/W2963900797","https://openalex.org/W2964000362","https://openalex.org/W2964102336","https://openalex.org/W2964265968","https://openalex.org/W2974641549","https://openalex.org/W2999153233","https://openalex.org/W3008003211","https://openalex.org/W3021249612","https://openalex.org/W3025638325","https://openalex.org/W3104949911","https://openalex.org/W6600751047","https://openalex.org/W6601403641"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793","https://openalex.org/W4238204885"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"propose":[2],"a":[3,23,34],"new":[4],"first-order":[5],"method":[6,25,308],"for":[7,173,209],"minimizing":[8],"nonconvex":[9],"functions":[10],"with":[11,27,242],"Lipschitz":[12,289],"continuous":[13,17],"gradients":[14],"and":[15,111,131,145,185,232],"H\u00f6lder":[16,143],"Hessians.":[18],"The":[19],"proposed":[20,307],"algorithm":[21,223,277],"is":[22,40,224,309],"heavy-ball":[24],"equipped":[26],"two":[28],"particular":[29],"restart":[30],"mechanisms.":[31],"It":[32],"finds":[33],"solution":[35],"where":[36,114],"the":[37,142,152,186,238,243,276,287,292,306],"gradient":[38,112],"norm":[39],"less":[41],"than":[42],"$$\\varepsilon":[43,295],"$$":[44,226,296],"<mml:math":[45,67,119,134,158,177,192,213,227,249,266,297],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[46,68,120,135,159,178,193,214,228,250,267,298],"<mml:mi>\u03b5</mml:mi>":[47,88,164,198,299],"</mml:math>":[48,109,130,140,172,184,208,220,230,260,272,300],"in":[49],"$$O(H_{\\nu":[50],"}^{\\frac{1}{2":[51],"+":[52,59,63],"2":[53,64],"\\nu":[54,61,65],"}}":[55],"\\varepsilon":[56],"^{-":[57],"\\frac{4":[58],"3":[60],"}{2":[62],"}})$$":[66],"<mml:mrow>":[69,74,79,89,92,98,121,160,165,179,194,199,215,251],"<mml:mi>O</mml:mi>":[70,161,195],"<mml:mo>(</mml:mo>":[71,162,196],"<mml:msubsup>":[72],"<mml:mi>H</mml:mi>":[73,137,269],"<mml:mi>\u03bd</mml:mi>":[75,83,96,102,122,138,180,216,229,252,270],"</mml:mrow>":[76,84,97,103,105,108,129,168,171,183,204,207,219,259],"<mml:mfrac>":[77,91],"<mml:mn>1</mml:mn>":[78,127,218,257],"<mml:mn>2</mml:mn>":[80,82,99,101,167],"<mml:mo>+</mml:mo>":[81,94,100],"</mml:mfrac>":[85,104],"</mml:msubsup>":[86],"<mml:msup>":[87,163,197],"<mml:mo>-</mml:mo>":[90,166,200],"<mml:mn>4</mml:mn>":[93,203],"<mml:mn>3</mml:mn>":[95],"</mml:msup>":[106,169,205],"<mml:mo>)</mml:mo>":[107,170,206],"function":[110],"evaluations,":[113],"$$\\nu":[115,174,210,225,245],"\\in":[116,246],"[0,":[117,247],"1]$$":[118,248],"<mml:mo>\u2208</mml:mo>":[123,253],"<mml:mo>[</mml:mo>":[124,254],"<mml:mn>0</mml:mn>":[125,182,255],"<mml:mo>,</mml:mo>":[126,256],"<mml:mo>]</mml:mo>":[128,258],"$$H_{\\nu":[132,264],"}$$":[133,265],"<mml:msub>":[136,268],"</mml:msub>":[139,271],"are":[141],"exponent":[144],"constant,":[146],"respectively.":[147],"This":[148],"complexity":[149,240],"result":[150],"covers":[151],"classical":[153],"bound":[154,188,241],"of":[155,189,263],"$$O(\\varepsilon":[156,190],"^{-2})$$":[157],"=":[175,211],"0$$":[176],"<mml:mo>=</mml:mo>":[181,217],"state-of-the-art":[187],"^{-7/4})$$":[191],"<mml:mn>7</mml:mn>":[201],"<mml:mo>/</mml:mo>":[202],"1$$":[212],".":[221,273,301],"Our":[222],"-independent":[231],"thus":[233],"universal;":[234],"it":[235],"automatically":[236],"achieves":[237],"above":[239],"optimal":[244],"without":[261],"knowledge":[262],"In":[274],"addition,":[275],"does":[278],"not":[279],"require":[280],"other":[281],"problem-dependent":[282],"parameters":[283],"as":[284],"input,":[285],"including":[286],"gradient\u2019s":[288],"constant":[290],"or":[291],"target":[293],"accuracy":[294],"Numerical":[302],"results":[303],"illustrate":[304],"that":[305],"promising.":[310]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}