{"id":"https://openalex.org/W2510191442","doi":"https://doi.org/10.1609/aaai.v30i1.10259","title":"Approximate K-Means++ in Sublinear Time","display_name":"Approximate K-Means++ in Sublinear Time","publication_year":2016,"publication_date":"2016-02-21","ids":{"openalex":"https://openalex.org/W2510191442","doi":"https://doi.org/10.1609/aaai.v30i1.10259","mag":"2510191442"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10259","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10259/10118","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10259/10118","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089890773","display_name":"Olivier Bachem","orcid":null},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olivier Bachem","raw_affiliation_strings":["Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)"],"affiliations":[{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)","institution_ids":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044677020","display_name":"Mario Lu\u010di\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mario Lucic","raw_affiliation_strings":["Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)"],"affiliations":[{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)","institution_ids":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078613749","display_name":"S. Hamed Hassani","orcid":null},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S. Hamed Hassani","raw_affiliation_strings":["Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)"],"affiliations":[{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)","institution_ids":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)"],"affiliations":[{"raw_affiliation_string":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETH Zurich)","institution_ids":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.491,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":113,"citation_normalized_percentile":{"value":0.999891,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"30","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998,"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":0.9981,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9969,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.7991025},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.67279035}],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.7991025},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.73398006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.69061697},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.67279035},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5095015},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48527786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47504142},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.4196561},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4143005},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32841098},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28371298},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.16614822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15694195},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.13584751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13024187},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10259","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10259/10118","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v30i1.10259","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10259/10118","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W130123586","https://openalex.org/W1530581016","https://openalex.org/W1535669030","https://openalex.org/W1556219185","https://openalex.org/W180242331","https://openalex.org/W1967187838","https://openalex.org/W1998325344","https://openalex.org/W2046816920","https://openalex.org/W2048442462","https://openalex.org/W2073459066","https://openalex.org/W2086943813","https://openalex.org/W2090948651","https://openalex.org/W2101012814","https://openalex.org/W2108399535","https://openalex.org/W2115665694","https://openalex.org/W2116762767","https://openalex.org/W2118190603","https://openalex.org/W2118858186","https://openalex.org/W2123297508","https://openalex.org/W2138309709","https://openalex.org/W2141650448","https://openalex.org/W2142827986","https://openalex.org/W2142838865","https://openalex.org/W2143776582","https://openalex.org/W2150593711","https://openalex.org/W2154200889","https://openalex.org/W2156499390","https://openalex.org/W2164573470","https://openalex.org/W2174057495","https://openalex.org/W2204035083","https://openalex.org/W4235023610","https://openalex.org/W4246464108","https://openalex.org/W4299874798"],"related_works":["https://openalex.org/W90906771","https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W3095877357","https://openalex.org/W3031039437","https://openalex.org/W2529185025","https://openalex.org/W2355833770","https://openalex.org/W2018828772","https://openalex.org/W1985458517","https://openalex.org/W183202219"],"abstract_inverted_index":{"The":[0,11,64],"quality":[1],"of":[2,23,105,117,148,158,161],"K-Means":[3,62],"clustering":[4,130],"is":[5,14,26,67,111,141],"extremely":[6],"sensitive":[7],"to":[8,15,18,46,68],"proper":[9],"initialization.":[10],"classic":[12],"remedy":[13],"apply":[16],"k-means++":[17,34,75,106,144],"obtain":[19,126],"an":[20],"initial":[21],"set":[22],"centers":[24],"that":[25,137],"provably":[27,128],"competitive":[28,142],"with":[29,76,143],"the":[30,40,70,95,97,101,115,138],"optimal":[31],"solution.":[32],"Unfortunately,":[33],"requires":[35],"k":[36],"full":[37,102],"passes":[38],"over":[39],"data":[41,118],"which":[42],"limits":[43],"its":[44,108],"applicability":[45],"massive":[47],"datasets.":[48],"We":[49,88],"address":[50],"this":[51],"problem":[52],"by":[53],"proposing":[54],"a":[55,77,127,146,154],"simple":[56],"and":[57],"efficient":[58],"seeding":[59],"algorithm":[60,99],"for":[61],"clustering.":[63],"main":[65],"idea":[66],"replace":[69],"exact":[71],"D2-sampling":[72],"step":[73],"in":[74,114,131,156],"substantially":[78],"faster":[79],"approximation":[80],"based":[81],"on":[82,94,145],"Markov":[83],"Chain":[84],"Monte":[85],"Carlo":[86],"sampling.":[87],"prove":[89],"that,":[90],"under":[91],"natural":[92],"assumptions":[93],"data,":[96],"proposed":[98,139],"retains":[100],"theoretical":[103],"guarantees":[104],"while":[107,152],"computational":[109],"complexity":[110],"only":[112],"sublinear":[113,132],"number":[116],"points.":[119],"For":[120],"such":[121],"datasets,":[122],"one":[123],"can":[124],"thus":[125],"good":[129],"time.":[133],"Extensive":[134],"experiments":[135],"confirm":[136],"method":[140],"variety":[147],"real-world,":[149],"large-scale":[150],"datasets":[151],"offering":[153],"reduction":[155],"runtime":[157],"several":[159],"orders":[160],"magnitude.":[162]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2510191442","counts_by_year":[{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2025-01-03T21:21:44.233841","created_date":"2016-09-16"}