{"id":"https://openalex.org/W4225383534","doi":"https://doi.org/10.1109/isit50566.2022.9834827","title":"Implicit Regularization Properties of Variance Reduced Stochastic Mirror Descent","display_name":"Implicit Regularization Properties of Variance Reduced Stochastic Mirror Descent","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4225383534","doi":"https://doi.org/10.1109/isit50566.2022.9834827"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834827","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.00058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108303345","display_name":"Yiling Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiling Luo","raw_affiliation_strings":["Georgia Institute of Technology,School of Industrial and Systems Engineering","School of Industrial and Systems Engineering, Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Industrial and Systems Engineering","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014880531","display_name":"Xiaoming Huo","orcid":"https://orcid.org/0000-0003-0101-1206"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoming Huo","raw_affiliation_strings":["Georgia Institute of Technology,School of Industrial and Systems Engineering","School of Industrial and Systems Engineering, Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Industrial and Systems Engineering","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005740286","display_name":"Yajun Mei","orcid":"https://orcid.org/0000-0002-1015-990X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajun Mei","raw_affiliation_strings":["Georgia Institute of Technology,School of Industrial and Systems Engineering","School of Industrial and Systems Engineering, Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Industrial and Systems Engineering","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108303345"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.5235,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61785127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"701"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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/T12676","display_name":"Machine Learning and ELM","score":0.9939000010490417,"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":0.7634586095809937},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6807907819747925},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.6690964698791504},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6324331760406494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5498462319374084},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5166881084442139},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4808422029018402},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.44881030917167664},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.4302588701248169},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4229007363319397},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40559035539627075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39698898792266846},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.25595197081565857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17061257362365723},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15889021754264832},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.10466018319129944},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10413160920143127}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7634586095809937},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6807907819747925},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.6690964698791504},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6324331760406494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5498462319374084},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5166881084442139},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4808422029018402},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.44881030917167664},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.4302588701248169},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4229007363319397},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40559035539627075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39698898792266846},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.25595197081565857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17061257362365723},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15889021754264832},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.10466018319129944},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10413160920143127},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit50566.2022.9834827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834827","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.00058","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.00058","pdf_url":"https://arxiv.org/pdf/2205.00058","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.00058","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.00058","pdf_url":"https://arxiv.org/pdf/2205.00058","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1568307856","https://openalex.org/W2107438106","https://openalex.org/W2304667012","https://openalex.org/W2806970110","https://openalex.org/W2810882972","https://openalex.org/W2924791586","https://openalex.org/W2962696654","https://openalex.org/W2963248893","https://openalex.org/W2963607709","https://openalex.org/W2996279083","https://openalex.org/W3003546594","https://openalex.org/W3011558670","https://openalex.org/W3042937252","https://openalex.org/W3114508735","https://openalex.org/W3120901154","https://openalex.org/W3132591740","https://openalex.org/W3148738583","https://openalex.org/W3191067499","https://openalex.org/W4225383534","https://openalex.org/W4288110775","https://openalex.org/W4288345424","https://openalex.org/W4288365839","https://openalex.org/W4388978179","https://openalex.org/W6676105031","https://openalex.org/W6698038680","https://openalex.org/W6734509502","https://openalex.org/W6752125765","https://openalex.org/W6753122105","https://openalex.org/W6760666519","https://openalex.org/W6762034364","https://openalex.org/W6763624801","https://openalex.org/W6766791369","https://openalex.org/W6771840336","https://openalex.org/W6775078174","https://openalex.org/W6785302414","https://openalex.org/W6788045047","https://openalex.org/W6788833324","https://openalex.org/W6790874890","https://openalex.org/W6791777456"],"related_works":["https://openalex.org/W2123107849","https://openalex.org/W2107438106","https://openalex.org/W2100475161","https://openalex.org/W4283750944","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668"],"abstract_inverted_index":{"In":[0,35],"machine":[1],"learning":[2],"and":[3,83],"statistical":[4],"data":[5],"analysis,":[6],"we":[7,148],"often":[8],"run":[9],"into":[10],"objective":[11],"function":[12],"that":[13,92,117],"is":[14,25,45,104,162],"a":[15,37,46,52,109,150],"summation:":[16],"the":[17,22,28,39,57,75,88,100,118,125,130,135,145,156,159,170],"number":[18],"of":[19,56,63,99,144,173],"terms":[20,98],"in":[21,97,129,155],"summation":[23],"possibly":[24],"equal":[26],"to":[27,94,124,168],"sample":[29],"size,":[30],"which":[31],"can":[32,66],"be":[33],"enormous.":[34],"such":[36,79,108],"setting,":[38],"stochastic":[40,84],"mirror":[41,127],"descent":[42,82,86],"(SMD)":[43],"algorithm":[44],"numerically":[47],"efficient":[48],"method\u2014each":[49],"iteration":[50],"involving":[51],"very":[53],"small":[54],"subset":[55],"data.":[58],"The":[59],"variance":[60],"reduction":[61],"version":[62],"SMD":[64,69],"(VRSMD)":[65],"further":[67],"improve":[68],"by":[70],"inducing":[71],"faster":[72],"convergence.":[73],"On":[74],"other":[76],"hand,":[77],"algorithms":[78],"as":[80],"gradient":[81,85],"have":[87],"implicit":[89,136],"regularization":[90,137],"property":[91,110,138],"leads":[93],"better":[95],"performance":[96],"generalization":[101],"errors.":[102],"Little":[103],"known":[105],"on":[106],"whether":[107],"holds":[111],"for":[112,139],"VRSMD.":[113,140,174],"We":[114,164],"prove":[115],"here":[116],"discrete":[119],"VRSMD":[120],"estimator":[121],"sequence":[122],"converges":[123],"minimum":[126],"interpolant":[128],"linear":[131],"regression.":[132],"This":[133],"establishes":[134],"As":[141],"an":[142],"application":[143],"above":[146],"result,":[147],"derive":[149],"model":[151,161],"estimation":[152],"accuracy":[153],"result":[154],"setting":[157],"when":[158],"true":[160],"sparse.":[163],"use":[165],"numerical":[166],"examples":[167],"illustrate":[169],"empirical":[171],"power":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-05-05T00:00:00"}