{"id":"https://openalex.org/W3016550448","doi":"https://doi.org/10.48550/arxiv.2004.06296","title":"Eigen Selection in Spectral Clustering: A Theory-Guided Practice","display_name":"Eigen Selection in Spectral Clustering: A Theory-Guided Practice","publication_year":2020,"publication_date":"2020-04-14","ids":{"openalex":"https://openalex.org/W3016550448","doi":"https://doi.org/10.48550/arxiv.2004.06296","mag":"3016550448"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2004.06296","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06296","pdf_url":"https://arxiv.org/pdf/2004.06296","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.06296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101913009","display_name":"Han Xiao","orcid":"https://orcid.org/0000-0002-9555-4342","observed_orcids":["https://orcid.org/0000-0002-9555-4342","https://orcid.org/0000-0002-3478-964X"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Xiao","raw_affiliation_strings":["International Institute of Finance , School of Management , University of Science and Technology of China","International Institute of Finance, School of Management, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Finance , School of Management , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"International Institute of Finance, School of Management, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071157779","display_name":"Xin Tong","orcid":"https://orcid.org/0000-0001-8534-3827","observed_orcids":["https://orcid.org/0000-0001-8534-3827"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong, Xin","raw_affiliation_strings":["Department of Data Sciences and Operations , Marshall School of Business , University of Southern California","University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Sciences and Operations , Marshall School of Business , University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029944120","display_name":"Yingying Fan","orcid":"https://orcid.org/0000-0003-1726-4654","observed_orcids":["https://orcid.org/0000-0003-1726-4654"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan, Yingying","raw_affiliation_strings":["Department of Data Sciences and Operations , Marshall School of Business , University of Southern California","Data Sciences and Operations, Department, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Sciences and Operations , Marshall School of Business , University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Data Sciences and Operations, Department, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8476999998092651,"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":0.8476999998092651,"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":0.09099999815225601,"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/T10136","display_name":"Statistical Methods and Inference","score":0.027300000190734863,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"spectral clustering","score":0.9520000219345093},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.7760000228881836},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.7300000190734863},{"id":"https://openalex.org/keywords/eigenvalue-multiplicity","display_name":"eigenvalue multiplicity","score":0.8450000286102295},{"id":"https://openalex.org/keywords/asymptotic-expansion","display_name":"asymptotic expansion","score":0.968999981880188},{"id":"https://openalex.org/keywords/clustering-stability","display_name":"clustering stability","score":0.6890000104904175}],"concepts":[{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.7642183303833008},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7527467012405396},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.7187947034835815},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5467896461486816},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5463826656341553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5263403654098511},{"id":"https://openalex.org/C156004811","wikidata":"https://www.wikidata.org/wiki/Q2228257","display_name":"Multiplicity (mathematics)","level":2,"score":0.46508070826530457},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4320451319217682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35816866159439087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3532981276512146},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2324865758419037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22181886434555054},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17476895451545715},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10661351680755615},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:arXiv.org:2004.06296","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06296","pdf_url":"https://arxiv.org/pdf/2004.06296","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"pmh:oai:figshare.com:article/14442246","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Eigen_selection_in_spectral_clustering_a_theory_guided_practice/14442246","pdf_url":"https://figshare.com/articles/journal_contribution/Eigen_selection_in_spectral_clustering_a_theory_guided_practice/14442246","source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2004.06296","doi":"https://doi.org/10.48550/arxiv.2004.06296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.06296","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.6084/m9.figshare.14442246","doi":"https://doi.org/10.6084/m9.figshare.14442246","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.14442246","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.6084/m9.figshare.14442246.v1","doi":"https://doi.org/10.6084/m9.figshare.14442246.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.14442246.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.6084/m9.figshare.14442246.v2","doi":"https://doi.org/10.6084/m9.figshare.14442246.v2","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.14442246.v2","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.06296","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.06296","pdf_url":"https://arxiv.org/pdf/2004.06296","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016550448.pdf","grobid_xml":"https://content.openalex.org/works/W3016550448.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1995241424","https://openalex.org/W2016381774","https://openalex.org/W2035076036","https://openalex.org/W2035548721","https://openalex.org/W2040313973","https://openalex.org/W2048178552","https://openalex.org/W2115568737","https://openalex.org/W2132914434","https://openalex.org/W2157875785","https://openalex.org/W2161367205","https://openalex.org/W2165874743","https://openalex.org/W2167689714","https://openalex.org/W2551931914","https://openalex.org/W2911742394","https://openalex.org/W2916037889","https://openalex.org/W2963836110","https://openalex.org/W2963903176","https://openalex.org/W2964298148","https://openalex.org/W3020570927","https://openalex.org/W3043617248","https://openalex.org/W3093072637","https://openalex.org/W3127939736"],"related_works":["https://openalex.org/W2282420652","https://openalex.org/W7096595333","https://openalex.org/W7168399277","https://openalex.org/W2290723974","https://openalex.org/W4288086739","https://openalex.org/W4220830728","https://openalex.org/W2117530015","https://openalex.org/W3011035757","https://openalex.org/W2165874743","https://openalex.org/W2393956121"],"abstract_inverted_index":{"Based":[0],"on":[1,28],"a":[2],"Gaussian":[3],"mixture":[4],"type":[5],"model":[6],"of":[7,33],"K":[8,88,94],"components,":[9],"we":[10],"derive":[11],"eigen":[12],"selection":[13,46,78],"procedures":[14,79],"that":[15],"improve":[16],"the":[17,29,41],"usual":[18],"spectral":[19,83],"clustering":[20,60,84],"algorithms":[21,100],"in":[22,112],"high-dimensional":[23],"settings,":[24],"which":[25],"typically":[26],"act":[27],"top":[30],"few":[31],"eigenvectors":[32,52,64],"an":[34],"affinity":[35],"matrix":[36,43],"(e.g.,":[37],"X\u22a4X)":[38],"derived":[39],"from":[40],"data":[42,118],"X.":[44],"Our":[45,77],"principle":[47],"formalizes":[48],"two":[49],"intuitions:":[50],"(1)":[51],"should":[53,70],"be":[54,71],"dropped":[55,72],"when":[56],"they":[57],"have":[58],"no":[59],"power;":[61],"(2)":[62],"some":[63],"corresponding":[65],"to":[66,74,81],"smaller":[67],"spiked":[68],"eigenvalues":[69],"due":[73],"estimation":[75],"inaccuracy.":[76],"lead":[80],"new":[82],"algorithms:":[85],"ESSC":[86],"for":[87,93],"=":[89],"2":[90],"and":[91,104,115],"GESSC":[92],">":[95],"2.":[96],"The":[97],"newly":[98],"proposed":[99],"enjoy":[101],"better":[102],"stability":[103],"compare":[105],"favorably":[106],"against":[107],"canonical":[108],"alternatives,":[109],"as":[110],"demonstrated":[111],"extensive":[113],"simulation":[114],"multiple":[116],"real":[117],"studies.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2020-04-24T00:00:00"}