{"id":"https://openalex.org/W2615341736","doi":"https://doi.org/10.1145/1412331.1412338","title":"Estimating statistical aggregates on probabilistic data streams","display_name":"Estimating statistical aggregates on probabilistic data streams","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2615341736","doi":"https://doi.org/10.1145/1412331.1412338","mag":"2615341736"},"language":"en","primary_location":{"id":"doi:10.1145/1412331.1412338","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1412331.1412338","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","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/A5023204485","display_name":"T. S. Jayram","orcid":"https://orcid.org/0000-0001-5235-4853"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. S. Jayram","raw_affiliation_strings":["IBM Almaden Research, Almaden, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research, Almaden, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979548","display_name":"Andrew McGregor","orcid":"https://orcid.org/0000-0002-2124-160X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McGregor","raw_affiliation_strings":["University of Massachusetts, Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075159410","display_name":"S. Muthukrishnan","orcid":"https://orcid.org/0009-0007-8936-5709"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Muthukrishnan","raw_affiliation_strings":["Google, Inc., New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049077665","display_name":"Erik Vee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Vee","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6384,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.9143645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"4","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9987999796867371,"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/T11106","display_name":"Data Management and Algorithms","score":0.9984999895095825,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.8372166156768799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7674959301948547},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.641555905342102},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5903350710868835},{"id":"https://openalex.org/keywords/probabilistic-database","display_name":"Probabilistic database","score":0.5663729310035706},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5284238457679749},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.49962854385375977},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4807543456554413},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4777785539627075},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47692081332206726},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4614265263080597},{"id":"https://openalex.org/keywords/probabilistic-analysis-of-algorithms","display_name":"Probabilistic analysis of algorithms","score":0.4479828476905823},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3018837571144104},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1960061490535736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19410482048988342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1388111114501953}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.8372166156768799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674959301948547},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.641555905342102},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5903350710868835},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.5663729310035706},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5284238457679749},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.49962854385375977},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4807543456554413},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4777785539627075},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47692081332206726},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4614265263080597},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.4479828476905823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3018837571144104},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1960061490535736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19410482048988342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1388111114501953},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.0},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1412331.1412338","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1412331.1412338","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1484190527","https://openalex.org/W1538558557","https://openalex.org/W1785933978","https://openalex.org/W1965972569","https://openalex.org/W1967505984","https://openalex.org/W1968461475","https://openalex.org/W1973266211","https://openalex.org/W1983266860","https://openalex.org/W1988967845","https://openalex.org/W1992609556","https://openalex.org/W1995484833","https://openalex.org/W2001474264","https://openalex.org/W2025051251","https://openalex.org/W2025177415","https://openalex.org/W2044334960","https://openalex.org/W2078686663","https://openalex.org/W2080745194","https://openalex.org/W2083613374","https://openalex.org/W2101366610","https://openalex.org/W2112452856","https://openalex.org/W2118224498","https://openalex.org/W2144261930","https://openalex.org/W2148176468","https://openalex.org/W2165753192","https://openalex.org/W2562755098"],"related_works":["https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W4361801939","https://openalex.org/W2802243998","https://openalex.org/W1521014365","https://openalex.org/W2736127210"],"abstract_inverted_index":{"The":[0],"probabilistic":[1,25,45,79,96,108,121,173],"stream":[2,18,32,46,139],"model":[3,19],"was":[4],"introduced":[5],"by":[6,123],"Jayram":[7],"et":[8],"al.":[9],"[2007].":[10],"It":[11],"is":[12,21,62],"a":[13,34,38,44,48,51,78,95,112,136,143,188],"generalization":[14],"of":[15,30,40,55,65,94,103,169],"the":[16,31,66,83,91,101,151,157,167,185,193],"data":[17,122,138],"that":[20],"suited":[22],"to":[23,115,141],"handling":[24],"data,":[26],"where":[27,59],"each":[28,60],"item":[29,61],"represents":[33],"probability":[35],"distribution":[36,49],"over":[37,50,120],"set":[39],"possible":[41],"events.":[42],"Therefore,":[43],"determines":[47],"potentially":[52],"exponential":[53],"number":[54,168],"classical":[56,137],"deterministic":[57],"streams,":[58],"deterministically":[63],"one":[64,85],"domain":[67],"values.":[68],"We":[69,81,110,155],"present":[70,82,156],"algorithms":[71,88,161],"for":[72,89,107,128,146,162,183,191],"computing":[73],"commonly":[74],"used":[75],"aggregates":[76],"on":[77,172],"stream.":[80,97],"first":[84,158],"pass":[86],"streaming":[87,160],"estimating":[90,104,147,163,184,192],"expected":[92],"mean":[93],"Next,":[98],"we":[99,134],"consider":[100],"problem":[102],"frequency":[105,153],"moments":[106],"data.":[109],"propose":[111],"general":[113],"approach":[114],"obtain":[116,142],"unbiased":[117,125],"estimators":[118,126],"working":[119],"utilizing":[124],"designed":[127],"standard":[129],"streams.":[130,174],"Applying":[131],"this":[132],"approach,":[133],"extend":[135],"algorithm":[140,145,182,190],"one-pass":[144,181],"F":[148,164],"2":[149],",":[150,166],"second":[152],"moment.":[154],"known":[159],"0":[165],"distinct":[170],"items":[171],"Our":[175],"work":[176],"also":[177],"gives":[178],"an":[179],"efficient":[180],"median,":[186],"and":[187],"two-pass":[189],"range.":[194]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}