{"id":"https://openalex.org/W2032726409","doi":"https://doi.org/10.1109/bigdata.2013.6691737","title":"Exploring sketches for probability estimation with sublinear memory","display_name":"Exploring sketches for probability estimation with sublinear memory","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2032726409","doi":"https://doi.org/10.1109/bigdata.2013.6691737","mag":"2032726409"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3430065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029918720","display_name":"Anthony Kleerekoper","orcid":"https://orcid.org/0000-0002-3621-8568"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anthony Kleerekoper","raw_affiliation_strings":["School of Computer Science, The University of Manchester, UK","Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026069638","display_name":"Mikel Luj\u00e1n","orcid":"https://orcid.org/0000-0002-0842-1083"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mikel Lujan","raw_affiliation_strings":["School of Computer Science, The University of Manchester, UK","Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091107483","display_name":"Gavin Brown","orcid":"https://orcid.org/0000-0003-2261-9018"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gavin Brown","raw_affiliation_strings":["School of Computer Science, The University of Manchester, UK","Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029918720"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.4809,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75488148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"19","issue":null,"first_page":"79","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994000196456909,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9965000152587891,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7499351501464844},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.7423526048660278},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6317025423049927},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5748907923698425},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.537508487701416},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5170912742614746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5135719776153564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5113982558250427},{"id":"https://openalex.org/keywords/probability-estimation","display_name":"Probability estimation","score":0.4544657766819},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44374871253967285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.370122492313385},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3217479884624481},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1790757179260254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499351501464844},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.7423526048660278},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6317025423049927},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5748907923698425},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.537508487701416},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5170912742614746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135719776153564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5113982558250427},{"id":"https://openalex.org/C2983703474","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Probability estimation","level":2,"score":0.4544657766819},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44374871253967285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.370122492313385},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3217479884624481},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1790757179260254},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2013.6691737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:e-space.mmu.ac.uk:620220","is_oa":false,"landing_page_url":"https://e-space.mmu.ac.uk/view/authors/f043619457031d832fc5c4befc0a5310.html>,","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:zenodo.org:3430065","is_oa":true,"landing_page_url":"https://zenodo.org/record/3430065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3430065","is_oa":true,"landing_page_url":"https://zenodo.org/record/3430065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1493892051","https://openalex.org/W1556911442","https://openalex.org/W2060324268","https://openalex.org/W2064379477","https://openalex.org/W2080234606","https://openalex.org/W2099111195","https://openalex.org/W2115247131","https://openalex.org/W2119479037","https://openalex.org/W4249843299","https://openalex.org/W4285719527","https://openalex.org/W6629496199","https://openalex.org/W6677040099"],"related_works":["https://openalex.org/W90906771","https://openalex.org/W2018828772","https://openalex.org/W2529185025","https://openalex.org/W2809723425","https://openalex.org/W2052708136","https://openalex.org/W2005302727","https://openalex.org/W3082028334","https://openalex.org/W1973725449","https://openalex.org/W2216265843","https://openalex.org/W2670504206"],"abstract_inverted_index":{"As":[0],"data":[1,45,61],"sets":[2],"become":[3],"ever":[4],"larger":[5],"it":[6,30],"becomes":[7],"increasingly":[8],"complex":[9],"to":[10,16,117],"apply":[11],"traditional":[12],"machine":[13,27],"learning":[14,28],"techniques":[15],"them.":[17],"Feature":[18],"selection":[19],"can":[20,32,114],"greatly":[21],"reduce":[22],"the":[23,41,66,76,79,84,91,100,123],"computational":[24],"requirements":[25],"of":[26,43,55,68,78,86,102,122],"but":[29,70],"too":[31],"be":[33,115],"memory":[34],"intensive.":[35],"In":[36],"this":[37,89],"paper":[38],"we":[39,106],"explore":[40],"use":[42],"succinct":[44],"structures":[46,62],"called":[47],"sketches":[48],"for":[49,74,98],"probability":[50],"estimation":[51],"as":[52],"a":[53,119],"component":[54],"information":[56,111],"theoretic":[57,112],"feature":[58],"selection.":[59],"These":[60],"are":[63],"sublinear":[64],"in":[65],"number":[67],"items":[69,104],"were":[71],"designed":[72],"only":[73],"estimating":[75,99],"frequency":[77,101],"most":[80],"frequent":[81],"items.":[82],"To":[83],"best":[85],"our":[87],"knowledge":[88],"is":[90],"first":[92],"time":[93],"they":[94],"have":[95],"been":[96],"examined":[97],"all":[103],"and":[105],"find":[107],"that":[108],"often":[109],"some":[110],"measures":[113],"estimated":[116],"within":[118],"few":[120],"percent":[121],"correct":[124],"values.":[125]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}