{"id":"https://openalex.org/W2034417563","doi":"https://doi.org/10.1137/10079817x","title":"Efficient Stream Sampling for Variance-Optimal Estimation of Subset Sums","display_name":"Efficient Stream Sampling for Variance-Optimal Estimation of Subset Sums","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2034417563","doi":"https://doi.org/10.1137/10079817x","mag":"2034417563"},"language":"en","primary_location":{"id":"doi:10.1137/10079817x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/10079817x","pdf_url":null,"source":{"id":"https://openalex.org/S153560523","display_name":"SIAM Journal on Computing","issn_l":"0097-5397","issn":["0097-5397","1095-7111"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Computing","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/A5026385549","display_name":"Edith Cohen","orcid":"https://orcid.org/0000-0002-3926-8237"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Edith Cohen","raw_affiliation_strings":["edith@research.att.com and duffield@research.att.com and lund@research.att.com and mthorup@research.att.com#TAB#"],"affiliations":[{"raw_affiliation_string":"edith@research.att.com and duffield@research.att.com and lund@research.att.com and mthorup@research.att.com#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048558842","display_name":"Nick Duffield","orcid":"https://orcid.org/0000-0001-7211-1584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nick Duffield","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006699796","display_name":"Haim Kaplan","orcid":"https://orcid.org/0000-0001-9586-8002"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haim Kaplan","raw_affiliation_strings":["haimk@cs.tau.ac.il#TAB#"],"affiliations":[{"raw_affiliation_string":"haimk@cs.tau.ac.il#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022565251","display_name":"Carsten Lund","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carsten Lund","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039232562","display_name":"Mikkel Thorup","orcid":"https://orcid.org/0000-0001-5237-1709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikkel Thorup","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026385549"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":2.6415,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.9054281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"40","issue":"5","first_page":"1402","last_page":"1431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9980999827384949,"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/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/variance","display_name":"Variance (accounting)","score":0.7427842617034912},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6852237582206726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6401155591011047},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5944592952728271},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5663686990737915},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5405558347702026},{"id":"https://openalex.org/keywords/sampling-scheme","display_name":"Sampling scheme","score":0.530032217502594},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47988927364349365},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4673025608062744},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4548332393169403},{"id":"https://openalex.org/keywords/variance-components","display_name":"Variance components","score":0.43467289209365845},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4130696952342987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.26946958899497986},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.09950581192970276}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7427842617034912},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6852237582206726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6401155591011047},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5944592952728271},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5663686990737915},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5405558347702026},{"id":"https://openalex.org/C2985139394","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Sampling scheme","level":3,"score":0.530032217502594},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47988927364349365},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4673025608062744},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4548332393169403},{"id":"https://openalex.org/C3018076075","wikidata":"https://www.wikidata.org/wiki/Q1826427","display_name":"Variance components","level":2,"score":0.43467289209365845},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4130696952342987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26946958899497986},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.09950581192970276},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/10079817x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/10079817x","pdf_url":null,"source":{"id":"https://openalex.org/S153560523","display_name":"SIAM Journal on Computing","issn_l":"0097-5397","issn":["0097-5397","1095-7111"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Computing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.387.5770","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.387.5770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.research.att.com/~duffield/papers/varopt-final.pdf","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":35,"referenced_works":["https://openalex.org/W1519331563","https://openalex.org/W1909754222","https://openalex.org/W1964857063","https://openalex.org/W1965765215","https://openalex.org/W1965972569","https://openalex.org/W1977141583","https://openalex.org/W1979819093","https://openalex.org/W1982682305","https://openalex.org/W1993482412","https://openalex.org/W1995484833","https://openalex.org/W1997988698","https://openalex.org/W2001947543","https://openalex.org/W2015420561","https://openalex.org/W2020434732","https://openalex.org/W2029685080","https://openalex.org/W2030590905","https://openalex.org/W2031006315","https://openalex.org/W2036304306","https://openalex.org/W2045555847","https://openalex.org/W2049127440","https://openalex.org/W2085845250","https://openalex.org/W2089620427","https://openalex.org/W2097332592","https://openalex.org/W2111806841","https://openalex.org/W2113046370","https://openalex.org/W2119885577","https://openalex.org/W2144261930","https://openalex.org/W2144407406","https://openalex.org/W2146320425","https://openalex.org/W2152092514","https://openalex.org/W2156760512","https://openalex.org/W2624301084","https://openalex.org/W2752853835","https://openalex.org/W3145128584","https://openalex.org/W4233471163"],"related_works":["https://openalex.org/W4243229075","https://openalex.org/W2049350278","https://openalex.org/W965449117","https://openalex.org/W1964236691","https://openalex.org/W2221502901","https://openalex.org/W1596283885","https://openalex.org/W783524875","https://openalex.org/W2419095690","https://openalex.org/W4286008728","https://openalex.org/W1543900781"],"abstract_inverted_index":{"From":[0],"a":[1,12,16,49,182],"high":[2],"volume":[3],"stream":[4,163],"of":[5,15,31,39,44,67,77,88,110,130,148,161,176],"weighted":[6],"items,":[7],"we":[8,22,83],"want":[9],"to":[10,26,135],"maintain":[11],"generic":[13,46],"sample":[14,47],"certain":[17],"limited":[18],"size":[19,95,111],"k":[20,101,123],"that":[21,60],"can":[23],"later":[24],"use":[25],"estimate":[27],"the":[28,36,45,89,104,115,127,146,162],"total":[29],"weight":[30],"arbitrary":[32],"subsets.":[33],"This":[34],"is":[35,117,155,170],"classic":[37],"context":[38],"on-line":[40],"reservoir":[41,55],"sampling,":[42],"thinking":[43],"as":[48],"reservoir.":[50],"We":[51],"present":[52],"an":[53],"efficient":[54],"sampling":[56],"scheme,":[57],"$\\textnormal{\\sc":[58,70],"VarOptk}$,":[59],"dominates":[61],"all":[62,108],"previous":[63],"schemes":[64],"in":[65,164,181],"terms":[66],"estimation":[68,76],"quality.":[69],"VarOptk}$":[71],"provides":[72,141],"variance":[73,106,147],"optimal":[74,136],"unbiased":[75],"subset":[78,94],"sums.":[79],"More":[80],"precisely,":[81],"if":[82],"have":[84],"seen":[85],"n":[86],"items":[87,131],"stream,":[90],"then":[91],"for":[92,126,174],"any":[93,119],"m,":[96],"our":[97,139],"scheme":[98,121,140],"based":[99],"on":[100,145],"samples":[102,124,177],"minimizes":[103],"average":[105,137],"over":[107],"subsets":[109,150],"m.":[112],"In":[113,133],"fact,":[114],"optimality":[116],"against":[118],"off-line":[120],"with":[122],"tailored":[125],"concrete":[128],"set":[129],"seen.":[132],"addition":[134],"variance,":[138],"tighter":[142],"worst-case":[143],"bounds":[144],"particular":[149],"than":[151],"previously":[152],"possible.":[153],"It":[154],"efficient,":[156],"handling":[157],"each":[158],"new":[159],"item":[160],"$O(\\log":[165],"k)$":[166],"time.":[167],"Finally,":[168],"it":[169],"particularly":[171],"well":[172],"suited":[173],"combinations":[175],"from":[178],"different":[179],"streams":[180],"distributed":[183],"setting.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}