{"id":"https://openalex.org/W2147299230","doi":"https://doi.org/10.1109/isit.2009.5205937","title":"Minimum description length and clustering with exemplars","display_name":"Minimum description length and clustering with exemplars","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2147299230","doi":"https://doi.org/10.1109/isit.2009.5205937","mag":"2147299230"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2009.5205937","doi":"https://doi.org/10.1109/isit.2009.5205937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2009.5205937","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Information Theory","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5113671863","display_name":"Po\u2010Hsiang Lai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Hsiang Lai","raw_affiliation_strings":["Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO, USA","Department of Electrical and Systems Engineering, Washington University in St. Louis, MO, 63130 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, Washington University in St. Louis, MO, 63130 USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044333105","display_name":"Joseph A. O\u2019Sullivan","orcid":"https://orcid.org/0000-0003-1510-4876","observed_orcids":["https://orcid.org/0000-0003-1510-4876"]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph A. O'Sullivan","raw_affiliation_strings":["Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO, USA","Department of Electrical and Systems Engineering, Washington University in St. Louis, MO, 63130 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, Washington University in St. Louis, MO, 63130 USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051490260","display_name":"Robert B. Pless","orcid":"https://orcid.org/0000-0001-5775-8216","observed_orcids":["https://orcid.org/0000-0001-5775-8216"]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Pless","raw_affiliation_strings":["Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO, USA","Department of Computer Science and Engineering, Washington University in St. Louis, MO 63130 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, Washington University in St Louis, St Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University in St. Louis, MO 63130 USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":0.7528,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69993326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"76","issue":null,"first_page":"1318","last_page":"1322"},"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/T11901","display_name":"Bayesian Methods and Mixture Models","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"}},{"id":"https://openalex.org/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"minimum description length","score":0.9940000176429749},{"id":"https://openalex.org/keywords/density-based-clustering","display_name":"density-based clustering","score":0.7820000052452087},{"id":"https://openalex.org/keywords/similarity-based-clustering","display_name":"similarity-based clustering","score":0.984000027179718},{"id":"https://openalex.org/keywords/distance-based-clustering","display_name":"distance clustering","score":0.8619999885559082},{"id":"https://openalex.org/keywords/stochastic-complexity","display_name":"stochastic complexity","score":0.9010000228881836},{"id":"https://openalex.org/keywords/information-theoretic-clustering","display_name":"information-theoretic clustering","score":0.8159999847412109},{"id":"https://openalex.org/keywords/number-of-clusters-estimation","display_name":"optimal number of clusters","score":0.578000009059906},{"id":"https://openalex.org/keywords/clustering-algorithms","display_name":"clustering algorithms","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9057534337043762},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.7629578113555908},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.6802223920822144},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.6683443784713745},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.5686906576156616},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5651534199714661},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.5651023387908936},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.5644497275352478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5383954644203186},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5258139967918396},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4796581566333771},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44757112860679626},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.432546466588974},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.4275491237640381},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4214385747909546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41288912296295166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3908270597457886},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit.2009.5205937","doi":"https://doi.org/10.1109/isit.2009.5205937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2009.5205937","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Information Theory","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W79749824","https://openalex.org/W1585610988","https://openalex.org/W1997404989","https://openalex.org/W2068782468","https://openalex.org/W2102098892","https://openalex.org/W2106596127","https://openalex.org/W2121564430","https://openalex.org/W2128859735","https://openalex.org/W2132119275","https://openalex.org/W2142635246","https://openalex.org/W2146855196","https://openalex.org/W2153233077","https://openalex.org/W2165232124","https://openalex.org/W2295046650","https://openalex.org/W2340149117","https://openalex.org/W2591589908","https://openalex.org/W3193262203","https://openalex.org/W4210524419"],"related_works":["https://openalex.org/W2591589908","https://openalex.org/W1988157641","https://openalex.org/W83294241","https://openalex.org/W7098174287","https://openalex.org/W2293424800","https://openalex.org/W1493341512","https://openalex.org/W7095849520","https://openalex.org/W4410397724","https://openalex.org/W1592616853","https://openalex.org/W7097835426"],"abstract_inverted_index":{"We":[0,51,64,92],"propose":[1,65],"an":[2],"information-theoretic":[3],"clustering":[4,8,13,18,55,67,82,94],"framework":[5],"for":[6,89],"density-based":[7],"and":[9,24,37],"similarity":[10],"or":[11],"distance-based":[12],"with":[14],"objective":[15,87],"functions":[16],"of":[17,35,70],"performance":[19,95],"derived":[20],"from":[21,49],"stochastic":[22],"complexity":[23],"minimum":[25,75],"description":[26],"length":[27],"(MDL)":[28],"arguments.":[29],"Under":[30],"this":[31],"framework,":[32],"the":[33,84],"number":[34],"clusters":[36],"parameters":[38],"can":[39,56],"be":[40,57],"determined":[41],"in":[42],"a":[43,74],"principled":[44],"way":[45],"without":[46],"prior":[47],"knowledge":[48],"users.":[50],"show":[52],"that":[53],"similarity-based":[54,90],"viewed":[58],"as":[59],"combinatorial":[60],"optimization":[61],"on":[62,73,96],"graphs.":[63],"two":[66],"algorithms,":[68],"one":[69],"which":[71,79],"relies":[72],"arborescence":[76],"tree":[77],"algorithm":[78],"returns":[80],"optimal":[81],"under":[83],"proposed":[85],"MDL":[86],"function":[88],"clustering.":[91],"demonstrate":[93],"synthetic":[97],"data.":[98]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}