{"id":"https://openalex.org/W69989483","doi":null,"title":"The complexity of massive data set computations","display_name":"The complexity of massive data set computations","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W69989483","mag":"69989483"},"language":"en","primary_location":{"id":"mag:69989483","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1123797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5054834255","display_name":"Ziv Bar-Yossef","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziv Bar-Yossef","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103200572","display_name":"Christos H. Papadimitriou","orcid":"https://orcid.org/0009-0004-6462-2316","observed_orcids":["https://orcid.org/0009-0004-6462-2316"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos H. Papadimitriou","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":"https://orcid.org/0009-0004-6462-2316","affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.3403,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.94351949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.6488999724388123,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.6488999724388123,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.1964000016450882,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.05609999969601631,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.8399999737739563},{"id":"https://openalex.org/keywords/computational-lower-bounds","display_name":"computational lower bounds","score":0.6880000233650208},{"id":"https://openalex.org/keywords/sampling-model","display_name":"sampling model","score":0.6200000047683716},{"id":"https://openalex.org/keywords/communication-complexity","display_name":"communication complexity","score":0.9210000038146973},{"id":"https://openalex.org/keywords/one-way-communication-complexity","display_name":"one-way communication complexity","score":0.859000027179718},{"id":"https://openalex.org/keywords/frequency-moments","display_name":"frequency moments","score":0.9380000233650208},{"id":"https://openalex.org/keywords/selection-function","display_name":"selection function","score":0.5339999794960022},{"id":"https://openalex.org/keywords/statistical-moments","display_name":"statistical moments","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6570810675621033},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5999398231506348},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5406380295753479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5297098159790039},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5242017507553101},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5219259262084961},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.48950421810150146},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.4844112992286682},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4551513195037842},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41340014338493347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33365756273269653},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2526171803474426},{"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},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:69989483","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1123797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2401312511","https://openalex.org/W2107917944","https://openalex.org/W1017144906","https://openalex.org/W3038100932","https://openalex.org/W1761167196","https://openalex.org/W2152489475","https://openalex.org/W7098769704","https://openalex.org/W7097199350","https://openalex.org/W2166833396","https://openalex.org/W2010395872"],"abstract_inverted_index":{"Numerous":[0],"massive":[1],"data":[2,45,193,290],"sets,":[3],"ranging":[4],"from":[5,111],"flows":[6],"of":[7,12,53,71,78,86,107,167,174,180,216,221,261,265,277,311,317],"Internet":[8],"traffic":[9],"to":[10,30,136,148,185,284],"logs":[11],"supermarket":[13],"transactions,":[14],"have":[15],"emerged":[16],"during":[17],"the":[18,26,54,62,69,72,84,142,192,209,233,282],"past":[19],"few":[20],"years.":[21],"Their":[22],"overwhelming":[23],"size":[24],"and":[25,48,116,127,134,151,155,177,195,200,271,289,302,314,316,319],"typically":[27],"restricted":[28],"access":[29],"them":[31],"call":[32],"for":[33,104,141,163,191,208,232,244,248,267,294],"new":[34,63,175,213,263],"computational":[35],"models.":[36,73],"This":[37],"thesis":[38,66],"studies":[39],"three":[40],"such":[41,119],"models:":[42],"sampling":[43,143],"computations,":[44,47],"stream":[46,194,291],"sketch":[49,196],"computations.":[50],"\r\nWhile":[51],"most":[52],"previous":[55],"work":[56,223],"focused":[57],"on":[58,256,272],"designing":[59],"algorithms":[60],"in":[61,88,98,113,172],"models,":[64,90],"this":[65,222],"revolves":[67],"around":[68],"limitations":[70],"We":[74,100,204,280],"develop":[75,205],"a":[76,105,164,212,241,257,262,273],"suite":[77],"lower":[79,138,189,206,230,246,292],"bound":[80,139,231],"techniques":[81,140,146],"that":[82],"characterize":[83],"complexity":[85,229,266,269,288],"functions":[87,150],"these":[89],"indicating":[91],"which":[92,182],"problems":[93,310],"can":[94],"be":[95],"solved":[96],"efficiently":[97],"them.":[99],"derive":[101],"specific":[102],"bounds":[103,162,190,207,247,293],"multitude":[106],"practical":[108],"problems,":[109,296],"arising":[110],"applications":[112],"database,":[114],"networking,":[115],"information":[117],"retrieval,":[118],"as":[120],"frequency":[121,300],"statistics,":[122],"selection":[123],"functions,":[124,181],"statistical":[125,178,275],"moments,":[126,301],"distance":[128,304],"estimation.":[129,305],"\r\nWe":[130,187],"present":[131,240],"general,":[132],"powerful,":[133],"easy":[135,184],"use":[137,281],"model.":[144],"The":[145,252],"apply":[147],"all":[149],"address":[152],"both":[153],"oblivious":[154],"adaptive":[156],"sampling.":[157],"They":[158,169],"frequently":[159],"produce":[160],"optimal":[161,226],"wide":[165],"range":[166],"functions.":[168],"are":[170,183],"stated":[171],"terms":[173],"combinatorial":[176],"properties":[179],"calculate.":[186],"obtain":[188,285],"models":[197],"through":[198],"one-way":[199],"simultaneous":[201,227],"communication":[202,217,228,250,268,278,287],"complexity.":[203,218,251,279],"latter":[210],"via":[211],"information-theoretic":[214],"view":[215,276],"A":[219],"highlight":[220],"is":[224,254],"an":[225],"important":[234],"multi-party":[235,298],"set-disjointness":[236],"problem.":[237],"\r\nFinally,":[238],"we":[239],"powerful":[242],"method":[243,253],"proving":[245],"general":[249],"based":[255],"direct":[258],"sum":[259],"property":[260],"measure":[264],"protocols":[270],"novel":[274],"technique":[283],"improved":[286],"several":[295],"including":[297],"set-disjointness,":[299],"Lp":[303],"These":[306],"results":[307],"solve":[308],"open":[309],"Alon,":[312],"Matias,":[313],"Szegedy":[315],"Saks":[318],"Sun.":[320]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}