{"id":"https://openalex.org/W2963344912","doi":"https://doi.org/10.48550/arxiv.1703.00439","title":"Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization","display_name":"Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2963344912","doi":"https://doi.org/10.48550/arxiv.1703.00439","mag":"2963344912"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1703.00439","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.00439","pdf_url":"https://arxiv.org/pdf/1703.00439","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/1703.00439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065727065","display_name":"Tomoya Murata","orcid":"https://orcid.org/0000-0001-8917-3714","observed_orcids":["https://orcid.org/0000-0001-8917-3714"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murata, Tomoya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078812767","display_name":"Taiji Suzuki","orcid":"https://orcid.org/0000-0003-3459-1016","observed_orcids":["https://orcid.org/0000-0003-3459-1016"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzuki, Taiji","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":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"608","last_page":"617"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10545","display_name":"Optimization and Variational Analysis","score":0.0,"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/dual-averaging","display_name":"dual averaging","score":0.6880000233650208},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"variance reduction","score":0.8659999966621399},{"id":"https://openalex.org/keywords/mini-batch-optimization","display_name":"mini-batch optimization","score":0.6779999732971191},{"id":"https://openalex.org/keywords/regularized-empirical-risk-minimization","display_name":"regularized empirical risk minimization","score":0.9829999804496765},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"convex optimization","score":0.6869999766349792},{"id":"https://openalex.org/keywords/iteration-complexity","display_name":"iteration complexity","score":0.8700000047683716},{"id":"https://openalex.org/keywords/strongly-convex-objectives","display_name":"strongly convex objectives","score":0.847000002861023},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.5809999704360962}],"concepts":[{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.7307059168815613},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.7102800607681274},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5956990718841553},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5935632586479187},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.559665858745575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188218951225281},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4814136028289795},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.47102198004722595},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44682469964027405},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.44162362813949585},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4336523413658142},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4252397119998932},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.42136719822883606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41781190037727356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3432080149650574},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1473427414894104},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.07079920172691345},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1703.00439","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.00439","pdf_url":"https://arxiv.org/pdf/1703.00439","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.1703.00439","doi":"https://doi.org/10.48550/arxiv.1703.00439","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.00439","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":"mag:2963344912","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/6663-doubly-accelerated-stochastic-variance-reduced-dual-averaging-method-for-regularized-empirical-risk-minimization.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.00439","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.00439","pdf_url":"https://arxiv.org/pdf/1703.00439","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/G13745398","display_name":null,"funder_award_id":"26280009","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G2028714080","display_name":null,"funder_award_id":"25120012","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G2174102762","display_name":null,"funder_award_id":"15H05707","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G2786733248","display_name":null,"funder_award_id":"25730013","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G3891047358","display_name":null,"funder_award_id":"15H01678","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963344912.pdf","grobid_xml":"https://content.openalex.org/works/W2963344912.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1544875630","https://openalex.org/W1791038712","https://openalex.org/W1874232560","https://openalex.org/W1939652453","https://openalex.org/W1986046400","https://openalex.org/W2047152541","https://openalex.org/W2096199223","https://openalex.org/W2103628399","https://openalex.org/W2105875671","https://openalex.org/W2107438106","https://openalex.org/W2111453803","https://openalex.org/W2119200797","https://openalex.org/W2127447444","https://openalex.org/W2146482778","https://openalex.org/W2146502635","https://openalex.org/W2184634347","https://openalex.org/W2267911020","https://openalex.org/W2286027391","https://openalex.org/W2406665342","https://openalex.org/W2952215077","https://openalex.org/W3141595720","https://openalex.org/W3205975889"],"related_works":["https://openalex.org/W2293758787","https://openalex.org/W2935410731","https://openalex.org/W2108948681","https://openalex.org/W2740525496","https://openalex.org/W7097906022","https://openalex.org/W1948582444","https://openalex.org/W2722088290","https://openalex.org/W2106728335","https://openalex.org/W3048726414","https://openalex.org/W2889925437"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,122],"develop":[4],"a":[5,30],"new":[6,65],"accelerated":[7,91],"stochastic":[8,92],"gradient":[9,43],"method":[10,59,78,83,130],"for":[11,101,107,137],"efficiently":[12],"solving":[13],"the":[14,34,42,61,86,103,117,132],"convex":[15,112,142],"regularized":[16],"empirical":[17],"risk":[18],"minimization":[19],"problem":[20],"in":[21,33,126],"mini-batch":[22,39,87],"settings.":[23],"The":[24,54],"use":[25,50],"of":[26,51,56,63,89],"mini-batches":[27,100],"is":[28,60,116],"becoming":[29],"golden":[31],"standard":[32],"machine":[35],"learning":[36],"community,":[37],"because":[38],"settings":[40],"stabilize":[41],"estimate":[44],"and":[45,69,79,94,110,140],"can":[46],"easily":[47],"make":[48],"good":[49],"parallel":[52],"computing.":[53],"core":[55],"our":[57,64,76,82,129],"proposed":[58,77],"incorporation":[62],"\"double":[66],"acceleration\"":[67],"technique":[68],"variance":[70],"reduction":[71],"technique.":[72],"We":[73],"theoretically":[74],"analyze":[75],"show":[80,123],"that":[81,124],"much":[84],"improves":[85],"efficiencies":[88],"previous":[90],"methods,":[93],"essentially":[95],"only":[96],"needs":[97],"size":[98],"$\\sqrt{n}$":[99],"achieving":[102],"optimal":[104],"iteration":[105],"complexities":[106],"both":[108,138],"non-strongly":[109,139],"strongly":[111,141],"objectives,":[113],"where":[114],"$n$":[115],"training":[118],"set":[119],"size.":[120],"Further,":[121],"even":[125],"non-mini-batch":[127],"settings,":[128],"achieves":[131],"best":[133],"known":[134],"convergence":[135],"rate":[136],"objectives.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-07-30T00:00:00"}