{"id":"https://openalex.org/W4393187994","doi":"https://doi.org/10.1145/3639280","title":"Determining Exact Quantiles with Randomized Summaries","display_name":"Determining Exact Quantiles with Randomized Summaries","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4393187994","doi":"https://doi.org/10.1145/3639280"},"language":"en","primary_location":{"id":"doi:10.1145/3639280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639280","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639280","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070051456","display_name":"Ziling Chen","orcid":"https://orcid.org/0009-0008-3197-2722"},"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":"Ziling Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3197-2722","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079955858","display_name":"Haoquan Guan","orcid":"https://orcid.org/0009-0007-5412-4489"},"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":"Haoquan Guan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5412-4489","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084430029","display_name":"Shaoxu Song","orcid":"https://orcid.org/0000-0002-9503-2755"},"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":"Shaoxu Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9503-2755","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084887843","display_name":"Xiangdong Huang","orcid":"https://orcid.org/0000-0002-6868-4045"},"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":"Xiangdong Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6868-4045","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337653","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-1698-8992"},"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":"Chen Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1698-8992","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100373517","display_name":"Jianmin Wang","orcid":"https://orcid.org/0000-0001-6841-7943"},"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":"Jianmin Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6841-7943","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8984,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70444915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/quantile","display_name":"Quantile","score":0.9319363832473755},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7304222583770752},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.6660809516906738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6004169583320618},{"id":"https://openalex.org/keywords/randomized-algorithm","display_name":"Randomized algorithm","score":0.43396952748298645},{"id":"https://openalex.org/keywords/quantile-function","display_name":"Quantile function","score":0.4306577444076538},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.42984139919281006},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.426783949136734},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4200921058654785},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.39553290605545044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3662963807582855},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.354872465133667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34914863109588623},{"id":"https://openalex.org/keywords/cumulative-distribution-function","display_name":"Cumulative distribution function","score":0.2902108132839203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18146568536758423},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.13016897439956665}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.9319363832473755},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7304222583770752},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.6660809516906738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6004169583320618},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.43396952748298645},{"id":"https://openalex.org/C47121976","wikidata":"https://www.wikidata.org/wiki/Q3489473","display_name":"Quantile function","level":4,"score":0.4306577444076538},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.42984139919281006},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.426783949136734},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4200921058654785},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39553290605545044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3662963807582855},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.354872465133667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34914863109588623},{"id":"https://openalex.org/C103784038","wikidata":"https://www.wikidata.org/wiki/Q386228","display_name":"Cumulative distribution function","level":3,"score":0.2902108132839203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18146568536758423},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.13016897439956665},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639280","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3639280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639280","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2021969373","display_name":null,"funder_award_id":"92267203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2154614518","display_name":"\u65f6\u5e8f\u6570\u636e\u6e05\u7406\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4903748402","display_name":null,"funder_award_id":"92267203 62021002 62072265 62232005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7091651887","display_name":null,"funder_award_id":"62021002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7508556822","display_name":null,"funder_award_id":"62232005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393187994.pdf","grobid_xml":"https://content.openalex.org/works/W4393187994.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2000337320","https://openalex.org/W2044849727","https://openalex.org/W2059676477","https://openalex.org/W2068739275","https://openalex.org/W2112452856","https://openalex.org/W2151310484","https://openalex.org/W2173213060","https://openalex.org/W2294895103","https://openalex.org/W2798839954","https://openalex.org/W2963274201","https://openalex.org/W2963379900","https://openalex.org/W2971243175","https://openalex.org/W3014100324","https://openalex.org/W3030889859","https://openalex.org/W3088632142","https://openalex.org/W3098583838","https://openalex.org/W3100923768","https://openalex.org/W3117786929","https://openalex.org/W3125185075","https://openalex.org/W3125675327","https://openalex.org/W3148579566","https://openalex.org/W3167971312","https://openalex.org/W3196066353","https://openalex.org/W3197605116","https://openalex.org/W4255348059","https://openalex.org/W4289533942","https://openalex.org/W4381326806","https://openalex.org/W4386360257","https://openalex.org/W7139033639"],"related_works":["https://openalex.org/W3136930549","https://openalex.org/W2911373886","https://openalex.org/W2790774582","https://openalex.org/W2031337030","https://openalex.org/W2792247961","https://openalex.org/W4382774528","https://openalex.org/W4246717623","https://openalex.org/W2995743897","https://openalex.org/W4244340232","https://openalex.org/W2024765102"],"abstract_inverted_index":{"Quantiles":[0],"are":[1],"fundamental":[2],"statistics":[3],"in":[4,19,28,42,64,90,120,167,197,216,230],"various":[5],"data":[6,18,41,225],"science":[7],"tasks,":[8],"but":[9],"costly":[10],"to":[11,38,48,62,75,98,180,247],"compute,":[12],"e.g.,":[13],"by":[14,128],"loading":[15],"the":[16,40,51,54,68,77,100,117,129,135,140,154,181,206,213,224,241,248,265,269],"entire":[17],"memory":[20,25,65],"for":[21,66,138,185,212,227],"ranking.":[22],"With":[23],"limited":[24],"space,":[26],"prevalent":[27],"end":[29],"devices":[30],"or":[31],"databases":[32],"with":[33,113,143,170,251,268],"heavy":[34],"loads,":[35],"it":[36,58],"needs":[37],"scan":[39],"multiple":[43,219],"passes.":[44,156],"The":[45,189],"idea":[46],"is":[47,59],"gradually":[49],"shrink":[50,99],"range":[52,79,91,231],"of":[53,80,243,264],"queried":[55],"quantile":[56,118,162,220],"till":[57],"small":[60],"enough":[61],"fit":[63],"ranking":[67],"result.":[69],"Existing":[70],"methods":[71,250],"use":[72],"deterministic":[73,84,252,271],"sketches":[74,208],"determine":[76],"exact":[78,141,161],"quantile,":[81],"known":[82],"as":[83,108,194],"filter,":[85,126],"which":[86],"could":[87,222],"be":[88,210],"inefficient":[89],"shrinking.":[92],"In":[93],"this":[94],"study,":[95],"we":[96,133],"propose":[97],"ranges":[101],"more":[102],"aggressively,":[103],"using":[104],"randomized":[105,130,207],"summaries":[106],"such":[107],"KLL":[109],"sketch.":[110,131],"That":[111],"is,":[112],"a":[114,121,148,186,195],"high":[115],"probability":[116,150],"lies":[119],"smaller":[122],"range,":[123],"namely":[124],"probabilistic":[125,144,228],"determined":[127],"Specifically,":[132],"estimate":[134],"expected":[136,155],"passes":[137,169,226,261],"determining":[139],"quantiles":[142],"filters,":[145],"and":[146,237,262],"select":[147],"proper":[149],"that":[151,159],"can":[152,165,209],"minimize":[153],"Analyses":[157],"show":[158],"our":[160,244,256],"determination":[163],"method":[164,257],"terminate":[166],"P":[168],"1-\u03b4":[171],"confidence,":[172],"storing":[173],"O(N":[174],"1/P":[175],"logP-1/2P":[176],"(1/\u03b4))":[177],"items,":[178],"close":[179],"lower":[182],"bound":[183],"\u00d8mega(N1/P)":[184],"fixed":[187],"\u03b4.":[188],"approach":[190],"has":[191],"been":[192],"deployed":[193],"function":[196],"an":[198],"LSM-tree":[199],"based":[200],"time-series":[201],"database":[202],"Apache":[203],"IoTDB.":[204],"Remarkably,":[205],"pre-computed":[211],"immutable":[214],"SSTables":[215],"LSM-tree.":[217],"Moreover,":[218],"queries":[221],"share":[223],"filters":[229],"estimation.":[232],"Extensive":[233],"experiments":[234],"on":[235],"real":[236],"synthetic":[238],"datasets":[239],"demonstrate":[240],"superiority":[242],"proposal":[245],"compared":[246,267],"existing":[249],"filters.":[253],"On":[254],"average,":[255],"takes":[258],"0.48":[259],"fewer":[260],"18%":[263],"time":[266],"state-of-the-art":[270],"sketch":[272],"(GK":[273],"sketch).":[274]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}