Journal article 62 views 14 downloads
Scalar field restricted Boltzmann machine as an ultraviolet regulator
Physical Review D, Volume: 109, Issue: 3
Swansea University Authors:
Gert Aarts , Biagio Lucini
, Chanju Park
-
PDF | Version of Record
Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license.
Download (12.03MB)
DOI (Published version): 10.1103/physrevd.109.034521
Abstract
Restricted Boltzmann machines (RBMs) are well-known tools used in machine learning to learn probability distribution functions from data. We analyze RBMs with scalar fields on the nodes from the perspective of lattice field theory. Starting with the simplest case of Gaussian fields, we show that the...
Published in: | Physical Review D |
---|---|
ISSN: | 2470-0010 2470-0029 |
Published: |
American Physical Society (APS)
2024
|
Online Access: |
Check full text
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa65735 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
first_indexed |
2024-03-04T13:59:54Z |
---|---|
last_indexed |
2024-03-04T13:59:54Z |
id |
cronfa65735 |
recordtype |
SURis |
fullrecord |
<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>65735</id><entry>2024-03-04</entry><title>Scalar field restricted Boltzmann machine as an ultraviolet regulator</title><swanseaauthors><author><sid>1ba0dad382dfe18348ec32fc65f3f3de</sid><ORCID>0000-0002-6038-3782</ORCID><firstname>Gert</firstname><surname>Aarts</surname><name>Gert Aarts</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>7e6fcfe060e07a351090e2a8aba363cf</sid><ORCID>0000-0001-8974-8266</ORCID><firstname>Biagio</firstname><surname>Lucini</surname><name>Biagio Lucini</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>60c7e702548bc829b5cbe3040ac41e8e</sid><firstname>Chanju</firstname><surname>Park</surname><name>Chanju Park</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-03-04</date><deptcode>SPH</deptcode><abstract>Restricted Boltzmann machines (RBMs) are well-known tools used in machine learning to learn probability distribution functions from data. We analyze RBMs with scalar fields on the nodes from the perspective of lattice field theory. Starting with the simplest case of Gaussian fields, we show that the RBM acts as an ultraviolet regulator, with the cutoff determined by either the number of hidden nodes or a model mass parameter. We verify these ideas in the scalar field case, where the target distribution is known, and explore implications for cases where it is not known using the MNIST dataset. We also demonstrate that infrared modes are learnt quickest.</abstract><type>Journal Article</type><journal>Physical Review D</journal><volume>109</volume><journalNumber>3</journalNumber><paginationStart/><paginationEnd/><publisher>American Physical Society (APS)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2470-0010</issnPrint><issnElectronic>2470-0029</issnElectronic><keywords/><publishedDay>29</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-02-29</publishedDate><doi>10.1103/physrevd.109.034521</doi><url/><notes/><college>COLLEGE NANME</college><department>Physics</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SPH</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>SCOAP3</funders><projectreference/><lastEdited>2024-04-25T21:28:29.1629711</lastEdited><Created>2024-03-04T13:55:21.1988538</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Biosciences, Geography and Physics - Physics</level></path><authors><author><firstname>Gert</firstname><surname>Aarts</surname><orcid>0000-0002-6038-3782</orcid><order>1</order></author><author><firstname>Biagio</firstname><surname>Lucini</surname><orcid>0000-0001-8974-8266</orcid><order>2</order></author><author><firstname>Chanju</firstname><surname>Park</surname><order>3</order></author></authors><documents><document><filename>65735__30161__378cce2ee09c45bfa8bf703c346314ff.pdf</filename><originalFilename>65735.VoR.pdf</originalFilename><uploaded>2024-04-25T21:27:11.7997755</uploaded><type>Output</type><contentLength>12619048</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807> |
spelling |
v2 65735 2024-03-04 Scalar field restricted Boltzmann machine as an ultraviolet regulator 1ba0dad382dfe18348ec32fc65f3f3de 0000-0002-6038-3782 Gert Aarts Gert Aarts true false 7e6fcfe060e07a351090e2a8aba363cf 0000-0001-8974-8266 Biagio Lucini Biagio Lucini true false 60c7e702548bc829b5cbe3040ac41e8e Chanju Park Chanju Park true false 2024-03-04 SPH Restricted Boltzmann machines (RBMs) are well-known tools used in machine learning to learn probability distribution functions from data. We analyze RBMs with scalar fields on the nodes from the perspective of lattice field theory. Starting with the simplest case of Gaussian fields, we show that the RBM acts as an ultraviolet regulator, with the cutoff determined by either the number of hidden nodes or a model mass parameter. We verify these ideas in the scalar field case, where the target distribution is known, and explore implications for cases where it is not known using the MNIST dataset. We also demonstrate that infrared modes are learnt quickest. Journal Article Physical Review D 109 3 American Physical Society (APS) 2470-0010 2470-0029 29 2 2024 2024-02-29 10.1103/physrevd.109.034521 COLLEGE NANME Physics COLLEGE CODE SPH Swansea University SU Library paid the OA fee (TA Institutional Deal) SCOAP3 2024-04-25T21:28:29.1629711 2024-03-04T13:55:21.1988538 Faculty of Science and Engineering School of Biosciences, Geography and Physics - Physics Gert Aarts 0000-0002-6038-3782 1 Biagio Lucini 0000-0001-8974-8266 2 Chanju Park 3 65735__30161__378cce2ee09c45bfa8bf703c346314ff.pdf 65735.VoR.pdf 2024-04-25T21:27:11.7997755 Output 12619048 application/pdf Version of Record true Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. true eng https://creativecommons.org/licenses/by/4.0/ |
title |
Scalar field restricted Boltzmann machine as an ultraviolet regulator |
spellingShingle |
Scalar field restricted Boltzmann machine as an ultraviolet regulator Gert Aarts Biagio Lucini Chanju Park |
title_short |
Scalar field restricted Boltzmann machine as an ultraviolet regulator |
title_full |
Scalar field restricted Boltzmann machine as an ultraviolet regulator |
title_fullStr |
Scalar field restricted Boltzmann machine as an ultraviolet regulator |
title_full_unstemmed |
Scalar field restricted Boltzmann machine as an ultraviolet regulator |
title_sort |
Scalar field restricted Boltzmann machine as an ultraviolet regulator |
author_id_str_mv |
1ba0dad382dfe18348ec32fc65f3f3de 7e6fcfe060e07a351090e2a8aba363cf 60c7e702548bc829b5cbe3040ac41e8e |
author_id_fullname_str_mv |
1ba0dad382dfe18348ec32fc65f3f3de_***_Gert Aarts 7e6fcfe060e07a351090e2a8aba363cf_***_Biagio Lucini 60c7e702548bc829b5cbe3040ac41e8e_***_Chanju Park |
author |
Gert Aarts Biagio Lucini Chanju Park |
author2 |
Gert Aarts Biagio Lucini Chanju Park |
format |
Journal article |
container_title |
Physical Review D |
container_volume |
109 |
container_issue |
3 |
publishDate |
2024 |
institution |
Swansea University |
issn |
2470-0010 2470-0029 |
doi_str_mv |
10.1103/physrevd.109.034521 |
publisher |
American Physical Society (APS) |
college_str |
Faculty of Science and Engineering |
hierarchytype |
|
hierarchy_top_id |
facultyofscienceandengineering |
hierarchy_top_title |
Faculty of Science and Engineering |
hierarchy_parent_id |
facultyofscienceandengineering |
hierarchy_parent_title |
Faculty of Science and Engineering |
department_str |
School of Biosciences, Geography and Physics - Physics{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Biosciences, Geography and Physics - Physics |
document_store_str |
1 |
active_str |
0 |
description |
Restricted Boltzmann machines (RBMs) are well-known tools used in machine learning to learn probability distribution functions from data. We analyze RBMs with scalar fields on the nodes from the perspective of lattice field theory. Starting with the simplest case of Gaussian fields, we show that the RBM acts as an ultraviolet regulator, with the cutoff determined by either the number of hidden nodes or a model mass parameter. We verify these ideas in the scalar field case, where the target distribution is known, and explore implications for cases where it is not known using the MNIST dataset. We also demonstrate that infrared modes are learnt quickest. |
published_date |
2024-02-29T21:28:29Z |
_version_ |
1797339909710675968 |
score |
11.016235 |