{"id":"https://openalex.org/W2797637497","doi":"https://doi.org/10.1109/icassp.2018.8461328","title":"Large-Scale High-Dimensional Clustering with Fast Sketching","display_name":"Large-Scale High-Dimensional Clustering with Fast Sketching","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2797637497","doi":"https://doi.org/10.1109/icassp.2018.8461328","mag":"2797637497"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5087376727","display_name":"Antoine Chatalic","orcid":"https://orcid.org/0000-0003-2574-2417"},"institutions":[{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Antoine Chatalic","raw_affiliation_strings":["Universit\u00e9 de Rennes 1, France","PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Mod\u00e9lisation Audio (Campus de Beaulieu 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Rennes 1, France","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Mod\u00e9lisation Audio (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041230403","display_name":"R\u00e9mi Gribonval","orcid":"https://orcid.org/0000-0002-9450-8125"},"institutions":[{"id":"https://openalex.org/I4210133778","display_name":"Inria Rennes - Bretagne Atlantique Research Centre","ror":"https://ror.org/04040yw90","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Remi Gribonval","raw_affiliation_strings":["Inria Rennes, France","PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Mod\u00e9lisation Audio (Campus de Beaulieu 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Rennes, France","institution_ids":["https://openalex.org/I4210133778"]},{"raw_affiliation_string":"PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Mod\u00e9lisation Audio (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003197490","display_name":"Nicolas Keriven","orcid":"https://orcid.org/0000-0002-3846-8763"},"institutions":[{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Keriven","raw_affiliation_strings":["Universit\u00e9 de Rennes 1, France","PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Mod\u00e9lisation Audio (Campus de Beaulieu 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Rennes 1, France","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Mod\u00e9lisation Audio (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087376727"],"corresponding_institution_ids":["https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":1.3542,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85544208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4714","last_page":"4718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","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/T10637","display_name":"Advanced Clustering Algorithms Research","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/T11106","display_name":"Data Management and Algorithms","score":0.9969000220298767,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8025830984115601},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6937234401702881},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5974164009094238},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.569197952747345},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5673315525054932},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.5434288382530212},{"id":"https://openalex.org/keywords/high-dimensional","display_name":"High dimensional","score":0.5240969061851501},{"id":"https://openalex.org/keywords/quadratic-growth","display_name":"Quadratic growth","score":0.510833740234375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39547407627105713},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39351019263267517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2788975238800049},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22611457109451294}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8025830984115601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937234401702881},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5974164009094238},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.569197952747345},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5673315525054932},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.5434288382530212},{"id":"https://openalex.org/C3019722297","wikidata":"https://www.wikidata.org/wiki/Q4440864","display_name":"High dimensional","level":2,"score":0.5240969061851501},{"id":"https://openalex.org/C195956108","wikidata":"https://www.wikidata.org/wiki/Q7268362","display_name":"Quadratic growth","level":2,"score":0.510833740234375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39547407627105713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39351019263267517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2788975238800049},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22611457109451294},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01701121v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01701121","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://2018.ieeeicassp.org/","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1811937711","https://openalex.org/W1914047618","https://openalex.org/W2022704179","https://openalex.org/W2028995298","https://openalex.org/W2093813380","https://openalex.org/W2095293504","https://openalex.org/W2097665501","https://openalex.org/W2118563516","https://openalex.org/W2135940344","https://openalex.org/W2144902422","https://openalex.org/W2150593711","https://openalex.org/W2151103935","https://openalex.org/W2155447220","https://openalex.org/W2165874743","https://openalex.org/W2252984395","https://openalex.org/W2417169585","https://openalex.org/W2504108613","https://openalex.org/W2540307294","https://openalex.org/W2594119225","https://openalex.org/W2605512869","https://openalex.org/W2794589353","https://openalex.org/W2949384808","https://openalex.org/W2979473749","https://openalex.org/W3115909054","https://openalex.org/W3127767495","https://openalex.org/W3148486289","https://openalex.org/W4205616900","https://openalex.org/W4294244666","https://openalex.org/W6629970164","https://openalex.org/W6638232957","https://openalex.org/W6640071562","https://openalex.org/W6674684338","https://openalex.org/W6677614981","https://openalex.org/W6679921305","https://openalex.org/W6681302627","https://openalex.org/W6684578312","https://openalex.org/W6689526104","https://openalex.org/W6691212913","https://openalex.org/W6713655233","https://openalex.org/W6717059847","https://openalex.org/W6728794588","https://openalex.org/W6728809436"],"related_works":["https://openalex.org/W4385270139","https://openalex.org/W3080491161","https://openalex.org/W3186815950","https://openalex.org/W2111119584","https://openalex.org/W2590034888","https://openalex.org/W4292621762","https://openalex.org/W2589483699","https://openalex.org/W3098102082","https://openalex.org/W2110877857","https://openalex.org/W3088133960"],"abstract_inverted_index":{"In":[0],"this":[1,34,61],"paper,":[2],"we":[3,74],"address":[4],"the":[5,39,53,67,85,100],"problem":[6],"of":[7,23,46],"high-dimensional":[8,72,97],"k-means":[9],"clustering":[10,101],"in":[11],"a":[12,20,43],"large-scale":[13],"setting,":[14],"i.e.":[15],"for":[16,96],"datasets":[17],"that":[18],"comprise":[19],"large":[21],"number":[22],"items.":[24],"Sketching":[25],"techniques":[26],"have":[27],"already":[28],"been":[29],"used":[30],"to":[31,69,77,83,105],"deal":[32],"with":[33,66,71],"\u201clarge-scale\u201d":[35],"issue,":[36],"by":[37],"compressing":[38],"whole":[40],"dataset":[41],"into":[42],"single":[44],"vector":[45],"random":[47,81],"nonlinear":[48],"generalized":[49],"moments":[50],"from":[51],"which":[52],"k":[54],"centroids":[55],"are":[56,103],"then":[57],"retrieved":[58],"efficiently.":[59,88],"However,":[60],"approach":[62],"usually":[63],"scales":[64],"quadratically":[65],"dimension;":[68],"cope":[70],"datasets,":[73],"show":[75],"how":[76],"use":[78],"fast":[79],"structured":[80],"matrices":[82],"compute":[84],"sketching":[86],"operator":[87],"This":[89],"yields":[90],"significant":[91],"speed-ups":[92],"and":[93,113],"memory":[94],"savings":[95],"data,":[98],"while":[99],"results":[102],"shown":[104],"be":[106],"much":[107],"more":[108],"stable,":[109],"both":[110],"on":[111],"artificial":[112],"real":[114],"datasets.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}