{"id":"https://openalex.org/W3036859713","doi":"https://doi.org/10.1137/18m1209854","title":"Turning Big Data Into Tiny Data: Constant-Size Coresets for $k$-Means, PCA, and Projective Clustering","display_name":"Turning Big Data Into Tiny Data: Constant-Size Coresets for $k$-Means, PCA, and Projective Clustering","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3036859713","doi":"https://doi.org/10.1137/18m1209854","mag":"3036859713"},"language":"en","primary_location":{"id":"doi:10.1137/18m1209854","is_oa":false,"landing_page_url":"https://doi.org/10.1137/18m1209854","pdf_url":null,"source":{"id":"https://openalex.org/S153560523","display_name":"SIAM Journal on Computing","issn_l":"0097-5397","issn":["0097-5397","1095-7111"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Computing","raw_type":"journal-article"},"type":"article","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/A5082255004","display_name":"Dan Feldman","orcid":"https://orcid.org/0000-0002-7700-9711"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dan Feldman","raw_affiliation_strings":["University of Haifa, Robotics & Big Data Lab"],"affiliations":[{"raw_affiliation_string":"University of Haifa, Robotics & Big Data Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037403363","display_name":"Melanie Schmidt","orcid":"https://orcid.org/0000-0003-4856-3905"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Melanie Schmidt","raw_affiliation_strings":["Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Germany,"],"affiliations":[{"raw_affiliation_string":"Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Germany,","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034247955","display_name":"Christian Sohler","orcid":"https://orcid.org/0000-0001-8990-3326"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Sohler","raw_affiliation_strings":["TU Dortmund, Germany,"],"affiliations":[{"raw_affiliation_string":"TU Dortmund, Germany,","institution_ids":["https://openalex.org/I200332995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082255004"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.5763,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99539232,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"49","issue":"3","first_page":"601","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"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/T10057","display_name":"Face and Expression Recognition","score":0.9984999895095825,"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/cardinality","display_name":"Cardinality (data modeling)","score":0.6805540323257446},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6258180141448975},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5659072399139404},{"id":"https://openalex.org/keywords/set-function","display_name":"Set function","score":0.540505588054657},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5126177668571472},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.49322646856307983},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4690811038017273},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4618481695652008},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.434266597032547},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3846001625061035},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3496374785900116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3040304183959961},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16719689965248108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15277135372161865}],"concepts":[{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6805540323257446},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6258180141448975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5659072399139404},{"id":"https://openalex.org/C15312841","wikidata":"https://www.wikidata.org/wiki/Q1657198","display_name":"Set function","level":3,"score":0.540505588054657},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5126177668571472},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.49322646856307983},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4690811038017273},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4618481695652008},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.434266597032547},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3846001625061035},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3496374785900116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3040304183959961},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16719689965248108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15277135372161865},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":2,"locations":[{"id":"doi:10.1137/18m1209854","is_oa":false,"landing_page_url":"https://doi.org/10.1137/18m1209854","pdf_url":null,"source":{"id":"https://openalex.org/S153560523","display_name":"SIAM Journal on Computing","issn_l":"0097-5397","issn":["0097-5397","1095-7111"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Computing","raw_type":"journal-article"},{"id":"pmh:oai:USBKOELN.ub.uni-koeln.de:11711","is_oa":false,"landing_page_url":"https://orcid.org/0000-0003-4856-3905>","pdf_url":null,"source":{"id":"https://openalex.org/S4306400371","display_name":"K\u00f6lner Universit\u00e4ts PublikationsServer (Universit\u00e4t zu K\u00f6ln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210115942","host_organization_name":"Rhenish Institute for Environmental Research","host_organization_lineage":["https://openalex.org/I4210115942"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1485437584","https://openalex.org/W1968301997","https://openalex.org/W1972949070","https://openalex.org/W1978906111","https://openalex.org/W1981313592","https://openalex.org/W1991417304","https://openalex.org/W1995484833","https://openalex.org/W2000646287","https://openalex.org/W2004791924","https://openalex.org/W2005423095","https://openalex.org/W2017476151","https://openalex.org/W2027402472","https://openalex.org/W2062567923","https://openalex.org/W2067081844","https://openalex.org/W2076257979","https://openalex.org/W2078841894","https://openalex.org/W2086959852","https://openalex.org/W2094048240","https://openalex.org/W2116940697","https://openalex.org/W2117756735","https://openalex.org/W2128227281","https://openalex.org/W2154952480","https://openalex.org/W2155429109","https://openalex.org/W2962963658","https://openalex.org/W2964283450","https://openalex.org/W3037079313","https://openalex.org/W3137387293"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2002177687","https://openalex.org/W2364594919","https://openalex.org/W2058438338","https://openalex.org/W2167092671","https://openalex.org/W2019471580","https://openalex.org/W275400387","https://openalex.org/W4364379828","https://openalex.org/W2247957169","https://openalex.org/W2027108423"],"abstract_inverted_index":{"We":[0],"develop":[1],"and":[2,135,204,232,263],"analyze":[3],"a":[4,11,19,25,36,85,101,108,173,229,250,271],"method":[5,220],"to":[6,24,187,284],"reduce":[7],"the":[8,33,42,47,52,59,65,71,77,82,89,97,119,122,128,132,137,148,166,177,180,207,214,226,234,237],"size":[9],"of":[10,15,28,35,64,76,84,114,121,127,131,147,155,168,179,213,216,236,253],"very":[12],"large":[13],"set":[14,27,44,67,79,91,103,124,175],"data":[16,38,254],"points":[17,30,227,238],"in":[18],"high-dimensional":[20],"Euclidean":[21],"space":[22,134],"$\\mathbb{R}^d$":[23],"small":[26],"weighted":[29],"such":[31,201],"that":[32,50,118,136,165,275,279],"result":[34],"predetermined":[37],"analysis":[39,255],"task":[40],"on":[41,88,153,223,228],"reduced":[43,66,90,102,123,170,174],"is":[45,104,117,125,172,221,270],"approximately":[46,70],"same":[48],"as":[49,107,202],"for":[51,96,176,249,281],"original":[53,78,98,182],"point":[54],"set.":[55,99],"For":[56,199],"example,":[57],"computing":[58,81],"first":[60,72],"$k$":[61,73],"principal":[62,74,260],"components":[63,75],"will":[68,92],"return":[69,93],"or":[80,193],"centers":[83],"$k$-means":[86,203,258],"clustering":[87],"an":[94,285],"approximation":[95,206],"Such":[100],"also":[105,211],"known":[106,243],"coreset.":[109],"The":[110,161,245,266],"main":[111,267],"new":[112,272],"feature":[113],"our":[115,189],"construction":[116],"cardinality":[120,235],"independent":[126,212],"dimension":[129],"$d$":[130],"input":[133,217],"sets":[138,171],"are":[139,210],"mergeable":[140],"[P.":[141],"K.":[142],"Agarwal":[143],"et":[144],"al.,":[145],"Proceedings":[146],"31st":[149],"ACM":[150],"SIGMOD-SIGACT-SIGAI":[151],"Symposium":[152],"Principals":[154],"Database":[156],"Systems,":[157],"2012,":[158],"pp.":[159],"23--34].":[160],"latter":[162],"property":[163],"means":[164],"union":[167,178],"two":[169,181],"sets.":[183],"It":[184],"allows":[185,276],"us":[186],"turn":[188],"methods":[190],"into":[191],"streaming":[192],"distributed":[194],"algorithms":[195],"using":[196,242],"standard":[197],"approaches.":[198],"problems":[200],"subspace":[205,231,241,264],"coreset":[208,273],"sizes":[209],"number":[215],"points.":[218],"Our":[219],"based":[222],"data-dependently":[224],"projecting":[225],"low-dimensional":[230],"reducing":[233],"inside":[239],"this":[240],"methods.":[244],"proposed":[246],"approach":[247],"works":[248],"wide":[251],"range":[252],"techniques":[256],"including":[257],"clustering,":[259],"component":[261],"analysis,":[262],"clustering.":[265],"conceptual":[268],"contribution":[269],"definition":[274],"charging":[277],"costs":[278],"appear":[280],"every":[282],"solution":[283],"additive":[286],"constant.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}