Diffusion models learn distributions generated by complex Langevin dynamics

Habibi, Diaa Eddin; Aarts, Gert; Wang, Lingxiao; Zhou, Kai

doi:10.22323/1.466.0039

Conference Paper/Proceeding/Abstract 120 views 30 downloads

Diffusion models learn distributions generated by complex Langevin dynamics

Diaa Eddin Habibi, Gert Aarts

, Lingxiao Wang, Kai Zhou

Proceedings of The 41st International Symposium on Lattice Field Theory — PoS(LATTICE2024), Volume: 466, Start page: 039

Swansea University Authors: Diaa Eddin Habibi, Gert Aarts

PDF | Version of Record

© Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).
Download (1.54MB)

Check full text

DOI (Published version): 10.22323/1.466.0039

Abstract

The probability distribution effectively sampled by a complex Langevin process for theories witha sign problem is not known a priori and notoriously hard to understand. Diffusion models, a classof generative AI, can learn distributions from data. In this contribution, we explore the ability ofdiffus...

Full description

Published in:	Proceedings of The 41st International Symposium on Lattice Field Theory — PoS(LATTICE2024)
ISSN:	1824-8039
Published:	Trieste, Italy Sissa Medialab 2025
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa69013

first_indexed	2025-03-04T16:01:44Z
last_indexed	2025-04-25T05:20:08Z
id	cronfa69013
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-04-24T11:15:35.5203073</datestamp><bib-version>v2</bib-version><id>69013</id><entry>2025-03-04</entry><title>Diffusion models learn distributions generated by complex Langevin dynamics</title><swanseaauthors><author><sid>5d736de7adfea5495e2e56a4dcb42524</sid><firstname>Diaa Eddin</firstname><surname>Habibi</surname><name>Diaa Eddin Habibi</name><active>true</active><ethesisStudent>false</ethesisStudent></author><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></swanseaauthors><date>2025-03-04</date><deptcode>BGPS</deptcode><abstract>The probability distribution effectively sampled by a complex Langevin process for theories witha sign problem is not known a priori and notoriously hard to understand. Diffusion models, a classof generative AI, can learn distributions from data. In this contribution, we explore the ability ofdiffusion models to learn the distributions created by a complex Langevin process.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of The 41st International Symposium on Lattice Field Theory — PoS(LATTICE2024)</journal><volume>466</volume><journalNumber/><paginationStart>039</paginationStart><paginationEnd/><publisher>Sissa Medialab</publisher><placeOfPublication>Trieste, Italy</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1824-8039</issnElectronic><keywords/><publishedDay>13</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-01-13</publishedDate><doi>10.22323/1.466.0039</doi><url/><notes/><college>COLLEGE NANME</college><department>Biosciences Geography and Physics School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>BGPS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>DEHis supportedby theUKRIAIMLACCDTEP/S023992/1. GAis supportedbySTFCConsolidatedGrantST/X000648/1.KZissupportedbytheCUHK-Shenzhen Universitydevelopment fundundergrantNo.UDF01003041andUDF03003041, andShenzhen PeacockfundunderNo.2023TC0179.</funders><projectreference/><lastEdited>2025-04-24T11:15:35.5203073</lastEdited><Created>2025-03-04T11:40:42.1453151</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>Diaa Eddin</firstname><surname>Habibi</surname><order>1</order></author><author><firstname>Gert</firstname><surname>Aarts</surname><orcid>0000-0002-6038-3782</orcid><order>2</order></author><author><firstname>Lingxiao</firstname><surname>Wang</surname><order>3</order></author><author><firstname>Kai</firstname><surname>Zhou</surname><order>4</order></author></authors><documents><document><filename>69013__34083__cdbd29b4b77347a9bd335750be9330dd.pdf</filename><originalFilename>69013.VoR.pdf</originalFilename><uploaded>2025-04-24T11:13:44.4992222</uploaded><type>Output</type><contentLength>1613761</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-04-24T11:15:35.5203073 v2 69013 2025-03-04 Diffusion models learn distributions generated by complex Langevin dynamics 5d736de7adfea5495e2e56a4dcb42524 Diaa Eddin Habibi Diaa Eddin Habibi true false 1ba0dad382dfe18348ec32fc65f3f3de 0000-0002-6038-3782 Gert Aarts Gert Aarts true false 2025-03-04 BGPS The probability distribution effectively sampled by a complex Langevin process for theories witha sign problem is not known a priori and notoriously hard to understand. Diffusion models, a classof generative AI, can learn distributions from data. In this contribution, we explore the ability ofdiffusion models to learn the distributions created by a complex Langevin process. Conference Paper/Proceeding/Abstract Proceedings of The 41st International Symposium on Lattice Field Theory — PoS(LATTICE2024) 466 039 Sissa Medialab Trieste, Italy 1824-8039 13 1 2025 2025-01-13 10.22323/1.466.0039 COLLEGE NANME Biosciences Geography and Physics School COLLEGE CODE BGPS Swansea University DEHis supportedby theUKRIAIMLACCDTEP/S023992/1. GAis supportedbySTFCConsolidatedGrantST/X000648/1.KZissupportedbytheCUHK-Shenzhen Universitydevelopment fundundergrantNo.UDF01003041andUDF03003041, andShenzhen PeacockfundunderNo.2023TC0179. 2025-04-24T11:15:35.5203073 2025-03-04T11:40:42.1453151 Faculty of Science and Engineering School of Biosciences, Geography and Physics - Physics Diaa Eddin Habibi 1 Gert Aarts 0000-0002-6038-3782 2 Lingxiao Wang 3 Kai Zhou 4 69013__34083__cdbd29b4b77347a9bd335750be9330dd.pdf 69013.VoR.pdf 2025-04-24T11:13:44.4992222 Output 1613761 application/pdf Version of Record true © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0). true eng https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en
title	Diffusion models learn distributions generated by complex Langevin dynamics
spellingShingle	Diffusion models learn distributions generated by complex Langevin dynamics Diaa Eddin Habibi Gert Aarts
title_short	Diffusion models learn distributions generated by complex Langevin dynamics
title_full	Diffusion models learn distributions generated by complex Langevin dynamics
title_fullStr	Diffusion models learn distributions generated by complex Langevin dynamics
title_full_unstemmed	Diffusion models learn distributions generated by complex Langevin dynamics
title_sort	Diffusion models learn distributions generated by complex Langevin dynamics
author_id_str_mv	5d736de7adfea5495e2e56a4dcb42524 1ba0dad382dfe18348ec32fc65f3f3de
author_id_fullname_str_mv	5d736de7adfea5495e2e56a4dcb42524_*_Diaa Eddin Habibi 1ba0dad382dfe18348ec32fc65f3f3de_*_Gert Aarts
author	Diaa Eddin Habibi Gert Aarts
author2	Diaa Eddin Habibi Gert Aarts Lingxiao Wang Kai Zhou
format	Conference Paper/Proceeding/Abstract
container_title	Proceedings of The 41st International Symposium on Lattice Field Theory — PoS(LATTICE2024)
container_volume	466
container_start_page	039
publishDate	2025
institution	Swansea University
issn	1824-8039
doi_str_mv	10.22323/1.466.0039
publisher	Sissa Medialab
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	The probability distribution effectively sampled by a complex Langevin process for theories witha sign problem is not known a priori and notoriously hard to understand. Diffusion models, a classof generative AI, can learn distributions from data. In this contribution, we explore the ability ofdiffusion models to learn the distributions created by a complex Langevin process.
published_date	2025-01-13T05:46:06Z
_version_	1837868061289349120
score	11.07004

Diffusion models learn distributions generated by complex Langevin dynamics

Similar Items