Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes

Mixture models are a standard tool in statistical analysis, widely used for density modeling and model-based clustering. Current approaches typically model the parameters of the mixture components as independent variables. This can result in overlapping or poorly separated clusters when either the n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Hanxi, Zhang, Boqian, Rao, Vinayak
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Sun, Hanxi
Zhang, Boqian
Rao, Vinayak
description Mixture models are a standard tool in statistical analysis, widely used for density modeling and model-based clustering. Current approaches typically model the parameters of the mixture components as independent variables. This can result in overlapping or poorly separated clusters when either the number of clusters or the form of the mixture components is misspecified. Such model misspecification can undermine the interpretability and simplicity of these mixture models. To address this problem, we propose a Bayesian mixture model with repulsion between mixture components. The repulsion is induced by a generalized Mat\'ern type-III repulsive point process model, obtained through a dependent sequential thinning scheme on a primary Poisson point process. We derive a novel and efficient Gibbs sampler for posterior inference, and demonstrate the utility of the proposed method on a number of synthetic and real-world problems.
doi_str_mv 10.48550/arxiv.2210.04140
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_04140</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_04140</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2210_041403</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMgIKGJgYmhhwMjg6JVamFmcm5ikEpRaU5hRnlqUq-GZWlJQWAen8lNSczLx0hfLMkgwF38SSGPXUojyFgPzMvBKFgKL85NTi4tRiHgbWtMSc4lReKM3NIO_mGuLsoQu2LL6gKDM3sagyHmRpPNhSY8IqAC5pNu4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes</title><source>arXiv.org</source><creator>Sun, Hanxi ; Zhang, Boqian ; Rao, Vinayak</creator><creatorcontrib>Sun, Hanxi ; Zhang, Boqian ; Rao, Vinayak</creatorcontrib><description>Mixture models are a standard tool in statistical analysis, widely used for density modeling and model-based clustering. Current approaches typically model the parameters of the mixture components as independent variables. This can result in overlapping or poorly separated clusters when either the number of clusters or the form of the mixture components is misspecified. Such model misspecification can undermine the interpretability and simplicity of these mixture models. To address this problem, we propose a Bayesian mixture model with repulsion between mixture components. The repulsion is induced by a generalized Mat\'ern type-III repulsive point process model, obtained through a dependent sequential thinning scheme on a primary Poisson point process. We derive a novel and efficient Gibbs sampler for posterior inference, and demonstrate the utility of the proposed method on a number of synthetic and real-world problems.</description><identifier>DOI: 10.48550/arxiv.2210.04140</identifier><language>eng</language><subject>Statistics - Methodology</subject><creationdate>2022-10</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.04140$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.04140$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Sun, Hanxi</creatorcontrib><creatorcontrib>Zhang, Boqian</creatorcontrib><creatorcontrib>Rao, Vinayak</creatorcontrib><title>Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes</title><description>Mixture models are a standard tool in statistical analysis, widely used for density modeling and model-based clustering. Current approaches typically model the parameters of the mixture components as independent variables. This can result in overlapping or poorly separated clusters when either the number of clusters or the form of the mixture components is misspecified. Such model misspecification can undermine the interpretability and simplicity of these mixture models. To address this problem, we propose a Bayesian mixture model with repulsion between mixture components. The repulsion is induced by a generalized Mat\'ern type-III repulsive point process model, obtained through a dependent sequential thinning scheme on a primary Poisson point process. We derive a novel and efficient Gibbs sampler for posterior inference, and demonstrate the utility of the proposed method on a number of synthetic and real-world problems.</description><subject>Statistics - Methodology</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMgIKGJgYmhhwMjg6JVamFmcm5ikEpRaU5hRnlqUq-GZWlJQWAen8lNSczLx0hfLMkgwF38SSGPXUojyFgPzMvBKFgKL85NTi4tRiHgbWtMSc4lReKM3NIO_mGuLsoQu2LL6gKDM3sagyHmRpPNhSY8IqAC5pNu4</recordid><startdate>20221008</startdate><enddate>20221008</enddate><creator>Sun, Hanxi</creator><creator>Zhang, Boqian</creator><creator>Rao, Vinayak</creator><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20221008</creationdate><title>Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes</title><author>Sun, Hanxi ; Zhang, Boqian ; Rao, Vinayak</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2210_041403</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Statistics - Methodology</topic><toplevel>online_resources</toplevel><creatorcontrib>Sun, Hanxi</creatorcontrib><creatorcontrib>Zhang, Boqian</creatorcontrib><creatorcontrib>Rao, Vinayak</creatorcontrib><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sun, Hanxi</au><au>Zhang, Boqian</au><au>Rao, Vinayak</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes</atitle><date>2022-10-08</date><risdate>2022</risdate><abstract>Mixture models are a standard tool in statistical analysis, widely used for density modeling and model-based clustering. Current approaches typically model the parameters of the mixture components as independent variables. This can result in overlapping or poorly separated clusters when either the number of clusters or the form of the mixture components is misspecified. Such model misspecification can undermine the interpretability and simplicity of these mixture models. To address this problem, we propose a Bayesian mixture model with repulsion between mixture components. The repulsion is induced by a generalized Mat\'ern type-III repulsive point process model, obtained through a dependent sequential thinning scheme on a primary Poisson point process. We derive a novel and efficient Gibbs sampler for posterior inference, and demonstrate the utility of the proposed method on a number of synthetic and real-world problems.</abstract><doi>10.48550/arxiv.2210.04140</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.04140
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_04140
source arXiv.org
subjects Statistics - Methodology
title Bayesian Repulsive Mixture Modeling with Mat\'ern Point Processes
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T09%3A52%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Bayesian%20Repulsive%20Mixture%20Modeling%20with%20Mat%5C'ern%20Point%20Processes&rft.au=Sun,%20Hanxi&rft.date=2022-10-08&rft_id=info:doi/10.48550/arxiv.2210.04140&rft_dat=%3Carxiv_GOX%3E2210_04140%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true