Algebraic Methods of Classifying Directed Graphical Models

Directed acyclic graphical models (DAGs) are often used to describe common structural properties in a family of probability distributions. This paper addresses the question of classifying DAGs up to an isomorphism. By considering Gaussian densities, the question reduces to verifying equality of cert...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Roozbehani, Hajir, Polyanskiy, Yury
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 Roozbehani, Hajir
Polyanskiy, Yury
description Directed acyclic graphical models (DAGs) are often used to describe common structural properties in a family of probability distributions. This paper addresses the question of classifying DAGs up to an isomorphism. By considering Gaussian densities, the question reduces to verifying equality of certain algebraic varieties. A question of computing equations for these varieties has been previously raised in the literature. Here it is shown that the most natural method adds spurious components with singular principal minors, proving a conjecture of Sullivant. This characterization is used to establish an algebraic criterion for isomorphism, and to provide a randomized algorithm for checking that criterion. Results are applied to produce a list of the isomorphism classes of tree models on 4,5, and 6 nodes. Finally, some evidence is provided to show that projectivized DAG varieties contain useful information in the sense that their relative embedding is closely related to efficient inference.
doi_str_mv 10.48550/arxiv.1401.5551
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1401_5551</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1401_5551</sourcerecordid><originalsourceid>FETCH-LOGICAL-a651-4591b1feb529a7254ffc679bb811aafc154dc048c28727f46f78783f56d3c0df3</originalsourceid><addsrcrecordid>eNotjz1PwzAUAL0woMLOhPwHEvISv9jpVgUoSK1YukfPH6-15JLKrhD996jAdNvpTogHaGplEJsnyt_xqwbVQI2IcCuWq7QPNlN0chvOh9kXObMcE5US-RI_9_I55uDOwct1ptMhOkpyO_uQyp24YUol3P9zIXavL7vxrdp8rN_H1aaiHqFSOIAFDhbbgXSLitn1erDWABCxA1TeNcq41uhWs-pZG206xt53rvHcLcTjn_a3fTrleKR8ma4P0_Wh-wGIp0DQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Algebraic Methods of Classifying Directed Graphical Models</title><source>arXiv.org</source><creator>Roozbehani, Hajir ; Polyanskiy, Yury</creator><creatorcontrib>Roozbehani, Hajir ; Polyanskiy, Yury</creatorcontrib><description>Directed acyclic graphical models (DAGs) are often used to describe common structural properties in a family of probability distributions. This paper addresses the question of classifying DAGs up to an isomorphism. By considering Gaussian densities, the question reduces to verifying equality of certain algebraic varieties. A question of computing equations for these varieties has been previously raised in the literature. Here it is shown that the most natural method adds spurious components with singular principal minors, proving a conjecture of Sullivant. This characterization is used to establish an algebraic criterion for isomorphism, and to provide a randomized algorithm for checking that criterion. Results are applied to produce a list of the isomorphism classes of tree models on 4,5, and 6 nodes. Finally, some evidence is provided to show that projectivized DAG varieties contain useful information in the sense that their relative embedding is closely related to efficient inference.</description><identifier>DOI: 10.48550/arxiv.1401.5551</identifier><language>eng</language><subject>Computer Science - Information Theory ; Mathematics - Information Theory ; Mathematics - Statistics Theory ; Statistics - Theory</subject><creationdate>2014-01</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,778,883</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1401.5551$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1401.5551$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Roozbehani, Hajir</creatorcontrib><creatorcontrib>Polyanskiy, Yury</creatorcontrib><title>Algebraic Methods of Classifying Directed Graphical Models</title><description>Directed acyclic graphical models (DAGs) are often used to describe common structural properties in a family of probability distributions. This paper addresses the question of classifying DAGs up to an isomorphism. By considering Gaussian densities, the question reduces to verifying equality of certain algebraic varieties. A question of computing equations for these varieties has been previously raised in the literature. Here it is shown that the most natural method adds spurious components with singular principal minors, proving a conjecture of Sullivant. This characterization is used to establish an algebraic criterion for isomorphism, and to provide a randomized algorithm for checking that criterion. Results are applied to produce a list of the isomorphism classes of tree models on 4,5, and 6 nodes. Finally, some evidence is provided to show that projectivized DAG varieties contain useful information in the sense that their relative embedding is closely related to efficient inference.</description><subject>Computer Science - Information Theory</subject><subject>Mathematics - Information Theory</subject><subject>Mathematics - Statistics Theory</subject><subject>Statistics - Theory</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotjz1PwzAUAL0woMLOhPwHEvISv9jpVgUoSK1YukfPH6-15JLKrhD996jAdNvpTogHaGplEJsnyt_xqwbVQI2IcCuWq7QPNlN0chvOh9kXObMcE5US-RI_9_I55uDOwct1ptMhOkpyO_uQyp24YUol3P9zIXavL7vxrdp8rN_H1aaiHqFSOIAFDhbbgXSLitn1erDWABCxA1TeNcq41uhWs-pZG206xt53rvHcLcTjn_a3fTrleKR8ma4P0_Wh-wGIp0DQ</recordid><startdate>20140121</startdate><enddate>20140121</enddate><creator>Roozbehani, Hajir</creator><creator>Polyanskiy, Yury</creator><scope>AKY</scope><scope>AKZ</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20140121</creationdate><title>Algebraic Methods of Classifying Directed Graphical Models</title><author>Roozbehani, Hajir ; Polyanskiy, Yury</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a651-4591b1feb529a7254ffc679bb811aafc154dc048c28727f46f78783f56d3c0df3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Computer Science - Information Theory</topic><topic>Mathematics - Information Theory</topic><topic>Mathematics - Statistics Theory</topic><topic>Statistics - Theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Roozbehani, Hajir</creatorcontrib><creatorcontrib>Polyanskiy, Yury</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Roozbehani, Hajir</au><au>Polyanskiy, Yury</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Algebraic Methods of Classifying Directed Graphical Models</atitle><date>2014-01-21</date><risdate>2014</risdate><abstract>Directed acyclic graphical models (DAGs) are often used to describe common structural properties in a family of probability distributions. This paper addresses the question of classifying DAGs up to an isomorphism. By considering Gaussian densities, the question reduces to verifying equality of certain algebraic varieties. A question of computing equations for these varieties has been previously raised in the literature. Here it is shown that the most natural method adds spurious components with singular principal minors, proving a conjecture of Sullivant. This characterization is used to establish an algebraic criterion for isomorphism, and to provide a randomized algorithm for checking that criterion. Results are applied to produce a list of the isomorphism classes of tree models on 4,5, and 6 nodes. Finally, some evidence is provided to show that projectivized DAG varieties contain useful information in the sense that their relative embedding is closely related to efficient inference.</abstract><doi>10.48550/arxiv.1401.5551</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1401.5551
ispartof
issn
language eng
recordid cdi_arxiv_primary_1401_5551
source arXiv.org
subjects Computer Science - Information Theory
Mathematics - Information Theory
Mathematics - Statistics Theory
Statistics - Theory
title Algebraic Methods of Classifying Directed Graphical Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T01%3A21%3A08IST&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=Algebraic%20Methods%20of%20Classifying%20Directed%20Graphical%20Models&rft.au=Roozbehani,%20Hajir&rft.date=2014-01-21&rft_id=info:doi/10.48550/arxiv.1401.5551&rft_dat=%3Carxiv_GOX%3E1401_5551%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