{"id":"https://openalex.org/W3035569828","doi":"https://doi.org/10.1145/3357713.3384296","title":"Coresets for clustering in Euclidean spaces: importance sampling is nearly optimal","display_name":"Coresets for clustering in Euclidean spaces: importance sampling is nearly optimal","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3035569828","doi":"https://doi.org/10.1145/3357713.3384296","mag":"3035569828"},"language":"en","primary_location":{"id":"doi:10.1145/3357713.3384296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357713.3384296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101420651","display_name":"Lingxiao Huang","orcid":"https://orcid.org/0000-0001-7512-142X"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingxiao Huang","raw_affiliation_strings":["Yale University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063089732","display_name":"Nisheeth K. Vishnoi","orcid":"https://orcid.org/0000-0002-0255-1119"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nisheeth K. Vishnoi","raw_affiliation_strings":["Yale University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":2.9961,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93027527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1416","last_page":"1429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9921000003814697,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9921000003814697,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9718999862670898,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9652000069618225,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.6861123442649841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6182811260223389},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5769603252410889},{"id":"https://openalex.org/keywords/euclidean-geometry","display_name":"Euclidean geometry","score":0.5555209517478943},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48403018712997437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.331218421459198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2842501401901245},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12601500749588013},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07270637154579163}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6861123442649841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182811260223389},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5769603252410889},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.5555209517478943},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48403018712997437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.331218421459198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2842501401901245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12601500749588013},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07270637154579163},{"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":"doi:10.1145/3357713.3384296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357713.3384296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G788184838","display_name":null,"funder_award_id":"CCF-1908347","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494933974","https://openalex.org/W1499729648","https://openalex.org/W1981773323","https://openalex.org/W2045964207","https://openalex.org/W2058295780","https://openalex.org/W2061902728","https://openalex.org/W2094048240","https://openalex.org/W2113238413","https://openalex.org/W2128968922","https://openalex.org/W2133157266","https://openalex.org/W2150593711","https://openalex.org/W2559873021","https://openalex.org/W2793950421","https://openalex.org/W2911597709","https://openalex.org/W2943587448","https://openalex.org/W2949910245","https://openalex.org/W2951203646","https://openalex.org/W2951931394","https://openalex.org/W2962682298","https://openalex.org/W2962691590","https://openalex.org/W2962777529","https://openalex.org/W3137423196","https://openalex.org/W3138444094","https://openalex.org/W4210896998","https://openalex.org/W4240768087"],"related_works":["https://openalex.org/W2090152127","https://openalex.org/W1965169884","https://openalex.org/W3125580510","https://openalex.org/W2008939113","https://openalex.org/W2033213447","https://openalex.org/W14679004","https://openalex.org/W1566651525","https://openalex.org/W2977652649","https://openalex.org/W2318206461","https://openalex.org/W37157938"],"abstract_inverted_index":{"Given":[0],"a":[1,19,59,88,111,150,162,187,197,203],"collection":[2],"of":[3,12,21,28,32,36,45,181,191,206],"n":[4],"points":[5],"in":[6,79,92,102,114,123,143,153],"\u211d":[7],"d":[8,90],",":[9],"the":[10,13,26,29,33,40,46,50,70,75,93,98,115,120,124,141,154],"goal":[11],"(k,z)-clustering":[14,47,71,78,101],"problem":[15,48],"is":[16,58],"to":[17,39,74,97,140],"find":[18],"subset":[20],"k":[22,151,209],"\u201ccenters\u201d":[23],"that":[24,65,167,216],"minimizes":[25],"sum":[27],"z-th":[30],"powers":[31],"Euclidean":[34],"distance":[35],"each":[37],"point":[38],"closest":[41],"center.":[42],"Special":[43],"cases":[44],"include":[49],"k-median":[51,131],"and":[52,81,104,118,145,176,178,210],"k-means":[53],"problems.":[54],"Our":[55,157],"main":[56],"result":[57,142],"unified":[60],"two-stage":[61],"importance":[62],"sampling":[63],"framework":[64,86,109],"constructs":[66],"an":[67,211],"\u03b5-coreset":[68],"for":[69,77,100,130,196,199],"problem.":[72],"Compared":[73,96],"results":[76,99,159],"[Feldman":[80],"Langberg,":[82],"STOC":[83,147],"2011],":[84],"our":[85,108,128,218],"saves":[87,110,149],"\u03b52":[89],"factor":[91,113,152],"coreset":[94,116,129,155],"size.":[95,156],"[Sohler":[103,144],"Woodruff,":[105,146],"FOCS":[106],"2018],":[107,148],"poly(k)":[112],"size":[117,134,188,207],"avoids":[119],"exp(k/\u03b5)":[121],"term":[122],"construction":[125],"time.":[126],"Specifically,":[127],"(z=1)":[132],"has":[133,202],"\u00d5(\u03b5\u22124":[135],"k)":[136],"which,":[137],"when":[138],"compared":[139],"algorithmic":[158,219],"rely":[160],"on":[161,208,214],"new":[163],"dimensionality":[164],"reduction":[165],"technique":[166],"connects":[168],"two":[169],"well-known":[170],"shape":[171],"fitting":[172],"problems:":[173],"subspace":[174],"approximation":[175],"clustering,":[177],"may":[179],"be":[180],"independent":[182],"interest.":[183],"We":[184],"also":[185],"provide":[186],"lower":[189],"bound":[190],"\u03a9(k\u00b7":[192],"min{2":[193],"z/20,d":[194],"})":[195],"0.01-coreset":[198],"(k,z)-clustering,":[200],"which":[201],"linear":[204],"dependence":[205,213],"exponential":[212],"z":[215],"matches":[217],"results.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}