{"id":"https://openalex.org/W2346474025","doi":"https://doi.org/10.1109/tkde.2016.2518679","title":"A Simple Message-Optimal Algorithm for Random Sampling from a Distributed Stream","display_name":"A Simple Message-Optimal Algorithm for Random Sampling from a Distributed Stream","publication_year":2016,"publication_date":"2016-01-18","ids":{"openalex":"https://openalex.org/W2346474025","doi":"https://doi.org/10.1109/tkde.2016.2518679","mag":"2346474025"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2016.2518679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2518679","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","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/A5029904435","display_name":"Yung-Yu Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yung-Yu Chung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Iowa State University, Ames, IA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047034711","display_name":"Srikanta Tirthapura","orcid":"https://orcid.org/0000-0001-5321-924X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikanta Tirthapura","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Iowa State University, Ames, IA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102861589","display_name":"David P. Woodruff","orcid":"https://orcid.org/0000-0002-2158-1380"},"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":"David P. Woodruff","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA 95120-6099"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA 95120-6099","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029904435"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":3.0921,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92830024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":"6","first_page":"1356","last_page":"1368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9976000189781189,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9976000189781189,"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":0.9966999888420105,"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/T12288","display_name":"Optimization and Search Problems","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.7893166542053223},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5857066512107849},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5701039433479309},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5129427313804626},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5003504753112793},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.49906063079833984},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.49244722723960876},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.4804913103580475},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4787147045135498},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4499255418777466},{"id":"https://openalex.org/keywords/asymptotically-optimal-algorithm","display_name":"Asymptotically optimal algorithm","score":0.42868858575820923},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4259006679058075},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41636741161346436},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41433802247047424},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.413473904132843},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.26046645641326904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16730675101280212},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.095969557762146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893166542053223},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5857066512107849},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5701039433479309},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5129427313804626},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5003504753112793},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.49906063079833984},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.49244722723960876},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.4804913103580475},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4787147045135498},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4499255418777466},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.42868858575820923},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4259006679058075},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41636741161346436},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41433802247047424},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.413473904132843},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26046645641326904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16730675101280212},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.095969557762146},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"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/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2016.2518679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2518679","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:lib.dr.iastate.edu:ece_pubs-1150","is_oa":false,"landing_page_url":"https://lib.dr.iastate.edu/ece_pubs/149","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1521238083","https://openalex.org/W1593168739","https://openalex.org/W1968625547","https://openalex.org/W1981663184","https://openalex.org/W1982682305","https://openalex.org/W1990465412","https://openalex.org/W2001183701","https://openalex.org/W2031034601","https://openalex.org/W2036035006","https://openalex.org/W2053154469","https://openalex.org/W2067467757","https://openalex.org/W2071989194","https://openalex.org/W2080527153","https://openalex.org/W2082553115","https://openalex.org/W2089297152","https://openalex.org/W2094308804","https://openalex.org/W2099941470","https://openalex.org/W2107443258","https://openalex.org/W2112400233","https://openalex.org/W2119163494","https://openalex.org/W2119885577","https://openalex.org/W2135730665","https://openalex.org/W2139076222","https://openalex.org/W2156632255","https://openalex.org/W2157268058","https://openalex.org/W2161317557","https://openalex.org/W2166767032","https://openalex.org/W3137191742","https://openalex.org/W4240264775","https://openalex.org/W6663682518","https://openalex.org/W6671428793","https://openalex.org/W6676268515","https://openalex.org/W6822210576"],"related_works":["https://openalex.org/W2347865597","https://openalex.org/W3148718598","https://openalex.org/W2163788280","https://openalex.org/W2012749513","https://openalex.org/W2105238802","https://openalex.org/W4295161910","https://openalex.org/W2008268605","https://openalex.org/W1557064786","https://openalex.org/W1647069448","https://openalex.org/W2136360692"],"abstract_inverted_index":{"We":[0,76,100],"present":[1,77],"a":[2,8,12,27,44,78,94],"simple,":[3],"message-optimal":[4],"algorithm":[5,123],"for":[6,119],"maintaining":[7],"random":[9,46],"sample":[10,47],"from":[11,48],"large":[13,98],"data":[14],"stream":[15],"whose":[16],"input":[17],"elements":[18,38,54,110],"are":[19],"distributed":[20],"across":[21,111],"multiple":[22],"sites":[23,113],"that":[24,83,118],"communicate":[25],"via":[26],"central":[28],"coordinator.":[29],"At":[30],"any":[31],"point":[32],"in":[33,73],"time,":[34],"the":[35,41,49,53,67,74,87,103,107],"set":[36,50],"of":[37,51,70,90,109],"held":[39],"by":[40],"coordinator":[42],"represent":[43],"uniform":[45],"all":[52],"observed":[55],"so":[56],"far.":[57],"When":[58],"compared":[59],"with":[60,97],"prior":[61,126],"work,":[62],"our":[63,84,122],"algorithms":[64],"asymptotically":[65],"improve":[66],"total":[68],"number":[69,89],"messages":[71,91],"sent":[72],"system.":[75],"matching":[79],"lower":[80],"bound,":[81],"showing":[82],"protocol":[85],"sends":[86],"optimal":[88],"up":[92],"to":[93],"constant":[95],"factor":[96],"probability.":[99],"also":[101],"consider":[102],"important":[104],"case":[105],"when":[106],"distribution":[108],"different":[112],"is":[114],"non-uniform,":[115],"and":[116],"show":[117],"such":[120],"inputs,":[121],"significantly":[124],"outperforms":[125],"solutions.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}