{"id":"https://openalex.org/W4280519736","doi":"https://doi.org/10.1109/tit.2022.3176955","title":"Sampling With Replacement vs Poisson Sampling: A Comparative Study in Optimal Subsampling","display_name":"Sampling With Replacement vs Poisson Sampling: A Comparative Study in Optimal Subsampling","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4280519736","doi":"https://doi.org/10.1109/tit.2022.3176955"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2022.3176955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2022.3176955","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067326549","display_name":"J. Wang","orcid":"https://orcid.org/0000-0001-6410-9935"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Department of Statistics, University of Connecticut, Storrs, CT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027190252","display_name":"Jiahui Zou","orcid":"https://orcid.org/0000-0002-3145-6807"},"institutions":[{"id":"https://openalex.org/I90259746","display_name":"Capital University of Economics and Business","ror":"https://ror.org/01r5sf951","country_code":"CN","type":"education","lineage":["https://openalex.org/I90259746"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Zou","raw_affiliation_strings":["School of Statistics, Capital University of Economics and Business, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics, Capital University of Economics and Business, Beijing, China","institution_ids":["https://openalex.org/I90259746"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100379056","display_name":"HaiYing Wang","orcid":"https://orcid.org/0000-0001-7729-0243"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HaiYing Wang","raw_affiliation_strings":["Department of Statistics, University of Connecticut, Storrs, CT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067326549"],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":4.1357,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94595895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"68","issue":"10","first_page":"6605","last_page":"6630"},"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":0.9930999875068665,"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":0.7926701307296753},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.7912313938140869},{"id":"https://openalex.org/keywords/poisson-sampling","display_name":"Poisson sampling","score":0.6253216862678528},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5751702189445496},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5742422938346863},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.543242871761322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5406216382980347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5071070194244385},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.48586317896842957},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46390125155448914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4531375467777252},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.42638713121414185},{"id":"https://openalex.org/keywords/slice-sampling","display_name":"Slice sampling","score":0.23557382822036743},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.16917690634727478}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7926701307296753},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.7912313938140869},{"id":"https://openalex.org/C82152865","wikidata":"https://www.wikidata.org/wiki/Q7208505","display_name":"Poisson sampling","level":5,"score":0.6253216862678528},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5751702189445496},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5742422938346863},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.543242871761322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5406216382980347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5071070194244385},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.48586317896842957},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46390125155448914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4531375467777252},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.42638713121414185},{"id":"https://openalex.org/C170593435","wikidata":"https://www.wikidata.org/wiki/Q4128565","display_name":"Slice sampling","level":4,"score":0.23557382822036743},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.16917690634727478},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2022.3176955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2022.3176955","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8092655725","display_name":null,"funder_award_id":"CCF-2105571","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1923722","https://openalex.org/W1460189015","https://openalex.org/W1545502309","https://openalex.org/W1920170482","https://openalex.org/W1970576574","https://openalex.org/W1971638458","https://openalex.org/W1983922269","https://openalex.org/W2001664148","https://openalex.org/W2003690406","https://openalex.org/W2006722592","https://openalex.org/W2007399394","https://openalex.org/W2020144485","https://openalex.org/W2029685080","https://openalex.org/W2035729201","https://openalex.org/W2042465463","https://openalex.org/W2099378941","https://openalex.org/W2101043704","https://openalex.org/W2116780995","https://openalex.org/W2125621954","https://openalex.org/W2141696759","https://openalex.org/W2146774335","https://openalex.org/W2320865122","https://openalex.org/W2327088997","https://openalex.org/W2513386243","https://openalex.org/W2559655401","https://openalex.org/W2596535828","https://openalex.org/W2766451779","https://openalex.org/W2962937842","https://openalex.org/W2964010828","https://openalex.org/W2975245449","https://openalex.org/W3044420422","https://openalex.org/W3098488568","https://openalex.org/W3099924168","https://openalex.org/W3106439409","https://openalex.org/W3112410551","https://openalex.org/W3120740533","https://openalex.org/W4212774754","https://openalex.org/W4213251304","https://openalex.org/W4231580960","https://openalex.org/W4242067627","https://openalex.org/W4244670803","https://openalex.org/W4293775970","https://openalex.org/W6610899768","https://openalex.org/W6674651100","https://openalex.org/W6675146241","https://openalex.org/W6677280552","https://openalex.org/W6729340713","https://openalex.org/W6744102197","https://openalex.org/W6745124860","https://openalex.org/W6748798142","https://openalex.org/W6767893161","https://openalex.org/W6793897105"],"related_works":["https://openalex.org/W3122602933","https://openalex.org/W2950038056","https://openalex.org/W1544940847","https://openalex.org/W2289285490","https://openalex.org/W2301330492","https://openalex.org/W3212973961","https://openalex.org/W2900543860","https://openalex.org/W2376641440","https://openalex.org/W3171633752","https://openalex.org/W2790158795"],"abstract_inverted_index":{"Faced":[0],"with":[1,34,119,149],"massive":[2],"data,":[3],"subsampling":[4,17,30,54,104,118,127,136,139,148,162,171],"is":[5,19,31],"a":[6,67,81,107,168],"commonly":[7],"used":[8],"technique":[9],"to":[10,23,47,166],"improve":[11,24],"computational":[12,28,62],"efficiency,":[13,29],"and":[14,61,121,145,151,157,193],"using":[15],"nonuniform":[16],"probabilities":[18,128,140],"an":[20],"effective":[21],"approach":[22,172],"estimation":[25,59,109],"efficiency.":[26,110],"For":[27],"often":[32],"implemented":[33],"replacement":[35,120,150],"or":[36],"through":[37,190],"Poisson":[38,103,122,152],"subsampling.":[39,153],"However,":[40],"no":[41],"rigorous":[42],"investigation":[43],"has":[44],"been":[45],"performed":[46],"study":[48,69],"the":[49,52,77,94,102,113,131,135,143,160,183],"difference":[50],"between":[51,147],"two":[53,72,95,161],"procedures":[55,163],"such":[56],"as":[57],"their":[58],"efficiency":[60],"convenience.":[63],"This":[64],"paper":[65],"performs":[66],"comparative":[68],"on":[70,112,159,182],"these":[71],"different":[73],"sampling":[74,96],"procedures.":[75,97],"In":[76],"context":[78],"of":[79,134],"maximizing":[80],"general":[82],"target":[83],"function,":[84],"we":[85,124],"first":[86],"derive":[87,125],"asymptotic":[88,114],"distributions":[89,115],"for":[90,116],"estimators":[91],"obtained":[92],"from":[93],"The":[98,154],"results":[99],"show":[100],"that":[101,129],"may":[105],"have":[106],"higher":[108],"Based":[111],"both":[117,191],"subsampling,":[123],"optimal":[126,184],"minimize":[130],"variance":[132],"functions":[133],"estimators.":[137],"These":[138],"further":[141],"reveal":[142],"similarities":[144],"differences":[146],"theoretical":[155,192],"characterizations":[156],"comparisons":[158],"provide":[164],"guidance":[165],"select":[167],"more":[169],"appropriate":[170],"in":[173],"practice.":[174],"Furthermore,":[175],"practically":[176],"implementable":[177],"algorithms":[178],"are":[179,188],"proposed":[180],"based":[181],"structural":[185],"results,":[186],"which":[187],"evaluated":[189],"empirical":[194],"analyses.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}