Quantitative Universal Approximation Bounds for Deep Belief Networks

Quantitative Universal Approximation Bounds for Deep Belief Networks

We show that deep belief networks with binary hidden units can approximate any multivariate probability density under very mild integrability requirements on the parental density of the visible nodes. The approximation is measured in the \(L^q\)-norm for \(q\in[1,\infty]\) (\(q=\infty\) correspondin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-08
Hauptverfasser: Sieber, Julian, Gehringer, Johann
Format: Artikel
Sprache:eng
Schlagworte:
Approximation
Belief networks
Density
Mathematical analysis
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Sieber, Julian
Gehringer, Johann
description We show that deep belief networks with binary hidden units can approximate any multivariate probability density under very mild integrability requirements on the parental density of the visible nodes. The approximation is measured in the \(L^q\)-norm for \(q\in[1,\infty]\) (\(q=\infty\) corresponding to the supremum norm) and in Kullback-Leibler divergence. Furthermore, we establish sharp quantitative bounds on the approximation error in terms of the number of hidden units.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2705198234</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2705198234</sourcerecordid><originalsourceid>FETCH-proquest_journals_27051982343</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwCSxNzCvJLEksySxLVQjNA5JFxYk5Co4FBUX5FZm5QPH8PAWn_NK8lGKFtPwiBZfU1AIFp9SczNQ0Bb_UkvL8ouxiHgbWtMSc4lReKM3NoOzmGuLsoQs0o7A0tbgkPiu_tCgPKBVvZG5gamhpYWRsYkycKgB--Dry</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2705198234</pqid></control><display><type>article</type><title>Quantitative Universal Approximation Bounds for Deep Belief Networks</title><source>Free E- Journals</source><creator>Sieber, Julian ; Gehringer, Johann</creator><creatorcontrib>Sieber, Julian ; Gehringer, Johann</creatorcontrib><description>We show that deep belief networks with binary hidden units can approximate any multivariate probability density under very mild integrability requirements on the parental density of the visible nodes. The approximation is measured in the \(L^q\)-norm for \(q\in[1,\infty]\) (\(q=\infty\) corresponding to the supremum norm) and in Kullback-Leibler divergence. Furthermore, we establish sharp quantitative bounds on the approximation error in terms of the number of hidden units.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Approximation ; Belief networks ; Density ; Mathematical analysis</subject><ispartof>arXiv.org, 2022-08</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Sieber, Julian</creatorcontrib><creatorcontrib>Gehringer, Johann</creatorcontrib><title>Quantitative Universal Approximation Bounds for Deep Belief Networks</title><title>arXiv.org</title><description>We show that deep belief networks with binary hidden units can approximate any multivariate probability density under very mild integrability requirements on the parental density of the visible nodes. The approximation is measured in the \(L^q\)-norm for \(q\in[1,\infty]\) (\(q=\infty\) corresponding to the supremum norm) and in Kullback-Leibler divergence. Furthermore, we establish sharp quantitative bounds on the approximation error in terms of the number of hidden units.</description><subject>Approximation</subject><subject>Belief networks</subject><subject>Density</subject><subject>Mathematical analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwCSxNzCvJLEksySxLVQjNA5JFxYk5Co4FBUX5FZm5QPH8PAWn_NK8lGKFtPwiBZfU1AIFp9SczNQ0Bb_UkvL8ouxiHgbWtMSc4lReKM3NoOzmGuLsoQs0o7A0tbgkPiu_tCgPKBVvZG5gamhpYWRsYkycKgB--Dry</recordid><startdate>20220818</startdate><enddate>20220818</enddate><creator>Sieber, Julian</creator><creator>Gehringer, Johann</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220818</creationdate><title>Quantitative Universal Approximation Bounds for Deep Belief Networks</title><author>Sieber, Julian ; Gehringer, Johann</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27051982343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Approximation</topic><topic>Belief networks</topic><topic>Density</topic><topic>Mathematical analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Sieber, Julian</creatorcontrib><creatorcontrib>Gehringer, Johann</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sieber, Julian</au><au>Gehringer, Johann</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Quantitative Universal Approximation Bounds for Deep Belief Networks</atitle><jtitle>arXiv.org</jtitle><date>2022-08-18</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>We show that deep belief networks with binary hidden units can approximate any multivariate probability density under very mild integrability requirements on the parental density of the visible nodes. The approximation is measured in the \(L^q\)-norm for \(q\in[1,\infty]\) (\(q=\infty\) corresponding to the supremum norm) and in Kullback-Leibler divergence. Furthermore, we establish sharp quantitative bounds on the approximation error in terms of the number of hidden units.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2705198234
source Free E- Journals
subjects Approximation
Belief networks
Density
Mathematical analysis
title Quantitative Universal Approximation Bounds for Deep Belief Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T09%3A59%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Quantitative%20Universal%20Approximation%20Bounds%20for%20Deep%20Belief%20Networks&rft.jtitle=arXiv.org&rft.au=Sieber,%20Julian&rft.date=2022-08-18&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2705198234%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2705198234&rft_id=info:pmid/&rfr_iscdi=true