{"id":"https://openalex.org/W4281770813","doi":"https://doi.org/10.1080/10618600.2022.2084404","title":"An Optimal Transport Approach for Selecting a Representative Subsample with Application in Efficient Kernel Density Estimation","display_name":"An Optimal Transport Approach for Selecting a Representative Subsample with Application in Efficient Kernel Density Estimation","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4281770813","doi":"https://doi.org/10.1080/10618600.2022.2084404"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2022.2084404","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2022.2084404","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/An_optimal_transport_approach_for_selecting_a_representative_subsample_with_application_in_efficient_kernel_density_estimation/20006529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007798612","display_name":"Jingyi Zhang","orcid":"https://orcid.org/0000-0002-3147-8838"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Zhang","raw_affiliation_strings":["Center for Statistical Science, Tsinghua University, Beijing, China;"],"raw_orcid":"https://orcid.org/0000-0002-3147-8838","affiliations":[{"raw_affiliation_string":"Center for Statistical Science, Tsinghua University, Beijing, China;","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102923021","display_name":"Cheng Meng","orcid":"https://orcid.org/0000-0002-7111-0966"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Meng","raw_affiliation_strings":["Center for Applied Statistics, Institute of Statistics and Big Data, Renmin University of China, Beijing, China;"],"raw_orcid":"https://orcid.org/0000-0002-7111-0966","affiliations":[{"raw_affiliation_string":"Center for Applied Statistics, Institute of Statistics and Big Data, Renmin University of China, Beijing, China;","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3390-5901"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Mathematics and Statistics, Beijing Institute of Technology, Beijing, China;"],"raw_orcid":"https://orcid.org/0000-0002-3390-5901","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Beijing Institute of Technology, Beijing, China;","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041179251","display_name":"Mengrui Zhang","orcid":"https://orcid.org/0000-0002-7082-3753"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengrui Zhang","raw_affiliation_strings":["Department of Statistics, University of Georgia, Athens, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Georgia, Athens, GA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103135389","display_name":"Wenxuan Zhong","orcid":"https://orcid.org/0000-0001-9006-622X"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenxuan Zhong","raw_affiliation_strings":["Department of Statistics, University of Georgia, Athens, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Georgia, Athens, GA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100664656","display_name":"Ping Ma","orcid":"https://orcid.org/0000-0002-5728-3596"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ping Ma","raw_affiliation_strings":["Department of Statistics, University of Georgia, Athens, GA"],"raw_orcid":"https://orcid.org/0000-0002-5728-3596","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Georgia, Athens, GA","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100664656"],"corresponding_institution_ids":["https://openalex.org/I165733156"],"apc_list":null,"apc_paid":null,"fwci":2.4971,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.905974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"329","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/estimator","display_name":"Estimator","score":0.7031351327896118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6505168676376343},{"id":"https://openalex.org/keywords/kernel-density-estimation","display_name":"Kernel density estimation","score":0.5831156969070435},{"id":"https://openalex.org/keywords/density-estimation","display_name":"Density estimation","score":0.4933086931705475},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4761362373828888},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.43942925333976746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38583219051361084},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38312503695487976},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3658851981163025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35020673274993896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3447865843772888},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24385622143745422},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2415476143360138}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7031351327896118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6505168676376343},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.5831156969070435},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.4933086931705475},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4761362373828888},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.43942925333976746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38583219051361084},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38312503695487976},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3658851981163025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35020673274993896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3447865843772888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24385622143745422},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2415476143360138},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1080/10618600.2022.2084404","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2022.2084404","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/20006529","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/An_optimal_transport_approach_for_selecting_a_representative_subsample_with_application_in_efficient_kernel_density_estimation/20006529","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.6084/m9.figshare.20006529.v2","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.20006529.v2","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20006529","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/An_optimal_transport_approach_for_selecting_a_representative_subsample_with_application_in_efficient_kernel_density_estimation/20006529","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1132625208","display_name":null,"funder_award_id":"12101606","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3299422055","display_name":null,"funder_award_id":"DMS-1903226","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3981035160","display_name":null,"funder_award_id":"12001042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7950052084","display_name":null,"funder_award_id":"2021YFA1001300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8582535629","display_name":null,"funder_award_id":"DMS-1925066","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306080","display_name":"Foundation for the National Institutes of Health","ror":"https://ror.org/00k86s890"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327514","display_name":"Beijing Institute of Technology Research Fund Program for Young Scholars","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W87152119","https://openalex.org/W648263199","https://openalex.org/W1594039573","https://openalex.org/W1918839972","https://openalex.org/W1968333723","https://openalex.org/W1968752677","https://openalex.org/W1978501336","https://openalex.org/W2006957355","https://openalex.org/W2007399394","https://openalex.org/W2010371250","https://openalex.org/W2015666727","https://openalex.org/W2019106840","https://openalex.org/W2024849762","https://openalex.org/W2025347578","https://openalex.org/W2039940482","https://openalex.org/W2041836242","https://openalex.org/W2042465463","https://openalex.org/W2056594234","https://openalex.org/W2068688638","https://openalex.org/W2080829915","https://openalex.org/W2082993877","https://openalex.org/W2083620785","https://openalex.org/W2097998671","https://openalex.org/W2098550720","https://openalex.org/W2101771965","https://openalex.org/W2109574129","https://openalex.org/W2117371776","https://openalex.org/W2128709328","https://openalex.org/W2133311553","https://openalex.org/W2141015396","https://openalex.org/W2160431995","https://openalex.org/W2161086299","https://openalex.org/W2162543061","https://openalex.org/W2165558283","https://openalex.org/W2396803061","https://openalex.org/W2539190955","https://openalex.org/W2559655401","https://openalex.org/W2576683119","https://openalex.org/W2596535828","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2606846509","https://openalex.org/W2883253089","https://openalex.org/W2949071206","https://openalex.org/W2955312852","https://openalex.org/W2964315040","https://openalex.org/W3022172246","https://openalex.org/W3028903392","https://openalex.org/W3037232215","https://openalex.org/W3043888703","https://openalex.org/W3047682456","https://openalex.org/W3166349013","https://openalex.org/W3214583003","https://openalex.org/W4206341000","https://openalex.org/W4206471589","https://openalex.org/W4206723194","https://openalex.org/W4211211011","https://openalex.org/W4212774754","https://openalex.org/W4213283575","https://openalex.org/W4214812430","https://openalex.org/W4238205818","https://openalex.org/W4243863038","https://openalex.org/W4252927802","https://openalex.org/W4280494023","https://openalex.org/W4300580367","https://openalex.org/W6640963894"],"related_works":["https://openalex.org/W1951523897","https://openalex.org/W2049836196","https://openalex.org/W2964081705","https://openalex.org/W2144201579","https://openalex.org/W4240479520","https://openalex.org/W3123419490","https://openalex.org/W2007242302","https://openalex.org/W4311428604","https://openalex.org/W1502956129","https://openalex.org/W4251895760"],"abstract_inverted_index":{"Subsampling":[0],"methods":[1,15,60,73,119],"aim":[2,45],"to":[3,46,103,144],"select":[4],"a":[5,8,48,77,82,124],"subsample":[6,98,155,171],"as":[7],"surrogate":[9],"for":[10,159,168,181],"the":[11,87,92,96,104,113,145,153,165,169,178,182,193,196],"observed":[12],"sample.":[13],"Such":[14,107],"have":[16],"been":[17],"used":[18,158],"pervasively":[19],"in":[20,29,36,120],"large-scale":[21],"data":[22],"analytics,":[23],"active":[24],"learning,":[25],"and":[26,109,189],"privacy-preserving":[27],"analysis":[28],"recent":[30],"decades.":[31],"Instead":[32],"of":[33,71,95,116,195],"model-based":[34],"methods,":[35,43],"this":[37],"article,":[38],"we":[39,135,151],"study":[40],"model-free":[41,58,117,126],"subsampling":[42,59,118,127,139],"which":[44],"identify":[47],"subsample,":[49],"that":[50,91,141],"is,":[51,142],"not":[52,100],"confined":[53],"by":[54,129,163],"model":[55],"assumptions.":[56],"Existing":[57],"are":[61],"usually":[62],"built":[63],"upon":[64],"clustering":[65],"techniques":[66],"or":[67,81],"kernel":[68,172],"tricks.":[69],"Most":[70],"these":[72],"suffer":[74],"from":[75],"either":[76],"large":[78],"computational":[79,108],"burden":[80],"theoretical":[83,88,110],"weakness.":[84],"In":[85],"particular,":[86],"weakness":[89],"is":[90,199],"empirical":[93],"distribution":[94],"selected":[97,154],"may":[99],"necessarily":[101],"converge":[102],"population":[105],"distribution.":[106],"limitations":[111],"hinder":[112],"broad":[114],"applicability":[115],"practice.":[121],"We":[122,175],"propose":[123],"novel":[125],"method":[128,198],"using":[130],"optimal":[131,179],"transport":[132],"techniques.":[133],"Moreover,":[134],"develop":[136],"an":[137],"efficient":[138,160],"algorithm,":[140],"adaptive":[143],"unknown":[146],"probability":[147],"density":[148,161,173],"function.":[149],"Theoretically,":[150],"show":[152],"can":[156],"be":[157],"estimation":[162],"deriving":[164],"convergence":[166],"rate":[167],"proposed":[170,183,197],"estimator.":[174,184],"also":[176],"provide":[177],"bandwidth":[180],"Numerical":[185],"studies":[186],"on":[187],"synthetic":[188],"real-world":[190],"datasets":[191],"demonstrate":[192],"performance":[194],"superior.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}