{"id":"https://openalex.org/W2216324198","doi":"https://doi.org/10.1145/2897518.2897527","title":"A cost function for similarity-based hierarchical clustering","display_name":"A cost function for similarity-based hierarchical clustering","publication_year":2016,"publication_date":"2016-06-10","ids":{"openalex":"https://openalex.org/W2216324198","doi":"https://doi.org/10.1145/2897518.2897527","mag":"2216324198"},"language":"en","primary_location":{"id":"doi:10.1145/2897518.2897527","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2897518.2897527","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2897527&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the forty-eighth annual ACM symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2897527&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101707744","display_name":"Sanjoy Dasgupta","orcid":"https://orcid.org/0000-0002-5960-5157"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanjoy Dasgupta","raw_affiliation_strings":["University of California at San Diego, USA","University of California at San Diego,USA"],"affiliations":[{"raw_affiliation_string":"University of California at San Diego, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California at San Diego,USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101707744"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.5091,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.61673493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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":0.9908999800682068,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6987981200218201},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6790159344673157},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6595730781555176},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6585819721221924},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6251122951507568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5893852114677429},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5535990595817566},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5135512351989746},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.5055673122406006},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41429126262664795},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37545686960220337},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3333839178085327},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32016417384147644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23257985711097717}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6987981200218201},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6790159344673157},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6595730781555176},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6585819721221924},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6251122951507568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893852114677429},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5535990595817566},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5135512351989746},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.5055673122406006},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41429126262664795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37545686960220337},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3333839178085327},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32016417384147644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23257985711097717},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2897518.2897527","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2897518.2897527","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2897527&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the forty-eighth annual ACM symposium on Theory of Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1510.05043","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1510.05043","pdf_url":"https://arxiv.org/pdf/1510.05043","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2216324198","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1510.05043","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1510.05043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1510.05043","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/2897518.2897527","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2897518.2897527","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2897527&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the forty-eighth annual ACM symposium on Theory of Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1176769941","display_name":"RI: Medium: Quantifying and utilizing confidence in machine learning","funder_award_id":"1162581","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3103558160","display_name":null,"funder_award_id":"IIS-1162581","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2216324198.pdf","grobid_xml":"https://content.openalex.org/works/W2216324198.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1605711022","https://openalex.org/W1963146503","https://openalex.org/W1989042829","https://openalex.org/W2007077266","https://openalex.org/W2016973429","https://openalex.org/W2034331023","https://openalex.org/W2055696239","https://openalex.org/W2064594923","https://openalex.org/W2085080020","https://openalex.org/W2088844265","https://openalex.org/W2132914434","https://openalex.org/W2150148016","https://openalex.org/W2161455936","https://openalex.org/W2769245605","https://openalex.org/W2787894218","https://openalex.org/W2963918728","https://openalex.org/W2989661724","https://openalex.org/W4388290228","https://openalex.org/W6770207831","https://openalex.org/W6817984829","https://openalex.org/W6830699988"],"related_works":["https://openalex.org/W2963737091","https://openalex.org/W1873229052","https://openalex.org/W2983181347","https://openalex.org/W2204944655","https://openalex.org/W2188030589","https://openalex.org/W2088857627","https://openalex.org/W3094286892","https://openalex.org/W2724116567","https://openalex.org/W2076702747","https://openalex.org/W2153320597","https://openalex.org/W2756390566","https://openalex.org/W3155989061","https://openalex.org/W2109509691","https://openalex.org/W2056187338","https://openalex.org/W3193954868","https://openalex.org/W2963051348","https://openalex.org/W2159609338","https://openalex.org/W2235617646","https://openalex.org/W2119611763","https://openalex.org/W2616785441"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,13,33],"algorithms":[3],"for":[4],"hierarchical":[5],"clustering":[6],"has":[7],"been":[8],"hampered":[9],"by":[10],"a":[11,24,31,55,60],"shortage":[12],"precise":[14],"objective":[15],"functions.":[16],"To":[17],"help":[18],"address":[19],"this":[20,44],"situation,":[21],"we":[22],"introduce":[23],"simple":[25],"cost":[26],"function":[27],"on":[28],"hierarchies":[29],"over":[30],"set":[32],"points,":[34],"given":[35],"pairwise":[36],"similarities":[37],"between":[38],"those":[39],"points.":[40],"We":[41],"show":[42],"that":[43,52],"criterion":[45],"behaves":[46],"sensibly":[47],"in":[48],"canonical":[49],"instances":[50],"and":[51],"it":[53],"admits":[54],"top-down":[56],"construction":[57],"procedure":[58],"with":[59],"provably":[61],"good":[62],"approximation":[63],"ratio.":[64]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}