{"id":"https://openalex.org/W2552050672","doi":null,"title":"Fast and Provably Good Seedings for k-Means","display_name":"Fast and Provably Good Seedings for k-Means","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2552050672","mag":"2552050672"},"language":"en","primary_location":{"id":"mag:2552050672","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/6478-fast-and-provably-good-seedings-for-k-means.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","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/A5089890773","display_name":"Olivier Bachem","orcid":null,"observed_orcids":[]},"institutions":[{"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":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044677020","display_name":"Mario Lu\u010di\u0107","orcid":"https://orcid.org/0009-0000-7826-2340","observed_orcids":["https://orcid.org/0009-0000-7826-2340"]},"institutions":[{"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 Lu\u010di\u0107","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059354479","display_name":"Hamed Hassani","orcid":"https://orcid.org/0000-0002-9448-8750","observed_orcids":["https://orcid.org/0000-0002-9448-8750"]},"institutions":[{"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":"Hamed Hassani","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-9448-8750","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["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","observed_orcids":["https://orcid.org/0000-0001-7260-9673"]},"institutions":[{"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":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-7260-9673","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":9.752,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.98382934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"55","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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":0.9994999766349792,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":9.999999747378752e-05,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":9.999999747378752e-05,"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/k-means-clustering","display_name":"K-means clustering","score":0.9079999923706055},{"id":"https://openalex.org/keywords/seeding","display_name":"seeding","score":0.5590000152587891},{"id":"https://openalex.org/keywords/cluster-center-initialization","display_name":"cluster center initialization","score":0.6990000009536743},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.7680000066757202},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.8896011710166931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687821388244629},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.5690913200378418},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5641632080078125},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5289050936698914},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5124459862709045},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4727688133716583},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.44033458828926086},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43166232109069824},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42604827880859375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41408973932266235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21988096833229065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1765979528427124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1718643605709076},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08264988660812378},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07474035024642944},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2552050672","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/6478-fast-and-provably-good-seedings-for-k-means.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1530581016","https://openalex.org/W1561129100","https://openalex.org/W2046816920","https://openalex.org/W2059515884","https://openalex.org/W2073459066","https://openalex.org/W2090948651","https://openalex.org/W2108399535","https://openalex.org/W2115665694","https://openalex.org/W2116762767","https://openalex.org/W2142838865","https://openalex.org/W2150593711","https://openalex.org/W2154200889","https://openalex.org/W2156499390","https://openalex.org/W2176996872","https://openalex.org/W2406025623","https://openalex.org/W2510191442"],"related_works":["https://openalex.org/W2510191442","https://openalex.org/W3103380776","https://openalex.org/W2988038483","https://openalex.org/W2405407512","https://openalex.org/W4407185639","https://openalex.org/W2242267102","https://openalex.org/W4409500033","https://openalex.org/W2073459066","https://openalex.org/W2555785574","https://openalex.org/W4365796160"],"abstract_inverted_index":{"Seeding":[0],"-":[1,9],"the":[2,21,24,45,63,74,95,101],"task":[3],"of":[4,23,66,123,136],"finding":[5],"initial":[6],"cluster":[7],"centers":[8],"is":[10,36],"critical":[11],"in":[12,130],"obtaining":[13],"high-quality":[14],"clusterings":[15,90],"for":[16,104],"k-Means.":[17],"However,":[18,68],"k-means++":[19,116],"seeding,":[20],"state":[22],"art":[25],"algorithm,":[26],"does":[27],"not":[28],"scale":[29],"well":[30],"to":[31,60,120],"massive":[32],"datasets":[33],"as":[34],"it":[35],"inherently":[37],"sequential":[38],"and":[39,111],"requires":[40,71],"k":[41],"full":[42],"passes":[43],"through":[44],"data.":[46,96],"It":[47],"was":[48],"recently":[49],"shown":[50],"that":[51,86,100],"Markov":[52],"chain":[53],"Monte":[54],"Carlo":[55],"sampling":[56],"can":[57],"be":[58],"used":[59],"efficiently":[61],"approximate":[62],"seeding":[64,84,117],"step":[65],"k-means++.":[67],"this":[69],"result":[70],"assumptions":[72],"on":[73,94,133],"data":[75,138],"generating":[76],"distribution.":[77],"We":[78,125],"propose":[79],"a":[80,105,134],"simple":[81],"yet":[82],"fast":[83],"algorithm":[85,102],"produces":[87],"*provably*":[88],"good":[89],"even":[91],"*without":[92],"assumptions*":[93],"Our":[97],"analysis":[98],"shows":[99],"allows":[103],"favourable":[106],"trade-off":[107],"between":[108],"solution":[109],"quality":[110],"computational":[112],"cost,":[113],"speeding":[114],"up":[115,119],"by":[118],"several":[121],"orders":[122],"magnitude.":[124],"validate":[126],"our":[127],"theoretical":[128],"results":[129],"extensive":[131],"experiments":[132],"variety":[135],"real-world":[137],"sets.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-11-30T00:00:00"}