High-Dimensional Inference in Bayesian Networks

Inference of the marginal probability distribution is defined as the calculation of the probability of a subset of the variables and is relevant for handling missing data and hidden variables. While inference of the marginal probability distribution is crucial for various problems in machine learnin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bayer, Fritz M, Moffa, Giusi, Beerenwinkel, Niko, Kuipers, Jack
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 Bayer, Fritz M
Moffa, Giusi
Beerenwinkel, Niko
Kuipers, Jack
description Inference of the marginal probability distribution is defined as the calculation of the probability of a subset of the variables and is relevant for handling missing data and hidden variables. While inference of the marginal probability distribution is crucial for various problems in machine learning and statistics, its exact computation is generally not feasible for categorical variables in Bayesian networks due to the NP-hardness of this task. We develop a divide-and-conquer approach using the graphical properties of Bayesian networks to split the computation of the marginal probability distribution into sub-calculations of lower dimensionality, thus reducing the overall computational complexity. Exploiting this property, we present an efficient and scalable algorithm for calculating the marginal probability distribution for categorical variables. The novel method is compared against state-of-the-art approximate inference methods in a benchmarking study, where it displays superior performance. As an immediate application, we demonstrate how our method can be used to classify incomplete data against Bayesian networks and use this approach for identifying the cancer subtype of kidney cancer patient samples.
doi_str_mv 10.48550/arxiv.2112.09217
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2112_09217</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2112_09217</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-1dbeca4d286f7410a0b61eac3d554235762b3a41a79c5086cfeaa9ae0f13c03d3</originalsourceid><addsrcrecordid>eNotzrtuwjAUgGEvDBXtA3RqXiCJj6_JWNJLkFC7sEcnznGxAFM5CMjbVwWmf_v1MfYMvFCV1rzEdAmnQgCIgtcC7AMr2_Czyd_CnuIYDhF32TJ6ShQdZSFmC5xoDBizLzqeD2k7PrKZx91IT_fO2frjfd20-er7c9m8rnI01uYw9ORQDaIy3irgyHsDhE4OWishtTWil6gAbe00r4zzhFgjcQ_ScTnIOXu5ba_i7jeFPaap-5d3V7n8A9m5Pag</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>High-Dimensional Inference in Bayesian Networks</title><source>arXiv.org</source><creator>Bayer, Fritz M ; Moffa, Giusi ; Beerenwinkel, Niko ; Kuipers, Jack</creator><creatorcontrib>Bayer, Fritz M ; Moffa, Giusi ; Beerenwinkel, Niko ; Kuipers, Jack</creatorcontrib><description>Inference of the marginal probability distribution is defined as the calculation of the probability of a subset of the variables and is relevant for handling missing data and hidden variables. While inference of the marginal probability distribution is crucial for various problems in machine learning and statistics, its exact computation is generally not feasible for categorical variables in Bayesian networks due to the NP-hardness of this task. We develop a divide-and-conquer approach using the graphical properties of Bayesian networks to split the computation of the marginal probability distribution into sub-calculations of lower dimensionality, thus reducing the overall computational complexity. Exploiting this property, we present an efficient and scalable algorithm for calculating the marginal probability distribution for categorical variables. The novel method is compared against state-of-the-art approximate inference methods in a benchmarking study, where it displays superior performance. As an immediate application, we demonstrate how our method can be used to classify incomplete data against Bayesian networks and use this approach for identifying the cancer subtype of kidney cancer patient samples.</description><identifier>DOI: 10.48550/arxiv.2112.09217</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2021-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2112.09217$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2112.09217$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bayer, Fritz M</creatorcontrib><creatorcontrib>Moffa, Giusi</creatorcontrib><creatorcontrib>Beerenwinkel, Niko</creatorcontrib><creatorcontrib>Kuipers, Jack</creatorcontrib><title>High-Dimensional Inference in Bayesian Networks</title><description>Inference of the marginal probability distribution is defined as the calculation of the probability of a subset of the variables and is relevant for handling missing data and hidden variables. While inference of the marginal probability distribution is crucial for various problems in machine learning and statistics, its exact computation is generally not feasible for categorical variables in Bayesian networks due to the NP-hardness of this task. We develop a divide-and-conquer approach using the graphical properties of Bayesian networks to split the computation of the marginal probability distribution into sub-calculations of lower dimensionality, thus reducing the overall computational complexity. Exploiting this property, we present an efficient and scalable algorithm for calculating the marginal probability distribution for categorical variables. The novel method is compared against state-of-the-art approximate inference methods in a benchmarking study, where it displays superior performance. As an immediate application, we demonstrate how our method can be used to classify incomplete data against Bayesian networks and use this approach for identifying the cancer subtype of kidney cancer patient samples.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrtuwjAUgGEvDBXtA3RqXiCJj6_JWNJLkFC7sEcnznGxAFM5CMjbVwWmf_v1MfYMvFCV1rzEdAmnQgCIgtcC7AMr2_Czyd_CnuIYDhF32TJ6ShQdZSFmC5xoDBizLzqeD2k7PrKZx91IT_fO2frjfd20-er7c9m8rnI01uYw9ORQDaIy3irgyHsDhE4OWishtTWil6gAbe00r4zzhFgjcQ_ScTnIOXu5ba_i7jeFPaap-5d3V7n8A9m5Pag</recordid><startdate>20211216</startdate><enddate>20211216</enddate><creator>Bayer, Fritz M</creator><creator>Moffa, Giusi</creator><creator>Beerenwinkel, Niko</creator><creator>Kuipers, Jack</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20211216</creationdate><title>High-Dimensional Inference in Bayesian Networks</title><author>Bayer, Fritz M ; Moffa, Giusi ; Beerenwinkel, Niko ; Kuipers, Jack</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-1dbeca4d286f7410a0b61eac3d554235762b3a41a79c5086cfeaa9ae0f13c03d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Bayer, Fritz M</creatorcontrib><creatorcontrib>Moffa, Giusi</creatorcontrib><creatorcontrib>Beerenwinkel, Niko</creatorcontrib><creatorcontrib>Kuipers, Jack</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bayer, Fritz M</au><au>Moffa, Giusi</au><au>Beerenwinkel, Niko</au><au>Kuipers, Jack</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>High-Dimensional Inference in Bayesian Networks</atitle><date>2021-12-16</date><risdate>2021</risdate><abstract>Inference of the marginal probability distribution is defined as the calculation of the probability of a subset of the variables and is relevant for handling missing data and hidden variables. While inference of the marginal probability distribution is crucial for various problems in machine learning and statistics, its exact computation is generally not feasible for categorical variables in Bayesian networks due to the NP-hardness of this task. We develop a divide-and-conquer approach using the graphical properties of Bayesian networks to split the computation of the marginal probability distribution into sub-calculations of lower dimensionality, thus reducing the overall computational complexity. Exploiting this property, we present an efficient and scalable algorithm for calculating the marginal probability distribution for categorical variables. The novel method is compared against state-of-the-art approximate inference methods in a benchmarking study, where it displays superior performance. As an immediate application, we demonstrate how our method can be used to classify incomplete data against Bayesian networks and use this approach for identifying the cancer subtype of kidney cancer patient samples.</abstract><doi>10.48550/arxiv.2112.09217</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2112.09217
ispartof
issn
language eng
recordid cdi_arxiv_primary_2112_09217
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title High-Dimensional Inference in Bayesian Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T22%3A07%3A11IST&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=High-Dimensional%20Inference%20in%20Bayesian%20Networks&rft.au=Bayer,%20Fritz%20M&rft.date=2021-12-16&rft_id=info:doi/10.48550/arxiv.2112.09217&rft_dat=%3Carxiv_GOX%3E2112_09217%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