DC Field
Value
Language
dc.contributor.author
Kazeykina, Anna
-
dc.contributor.author
Ren, Zhenjie
-
dc.contributor.author
Tan, Xiaolu
-
dc.contributor.author
Yang, Junjian
-
dc.date.accessioned
2024-07-22T10:47:18Z
-
dc.date.available
2024-07-22T10:47:18Z
-
dc.date.issued
2024-06
-
dc.identifier.citation
<div class="csl-bib-body"> <div class="csl-entry">Kazeykina, A., Ren, Z., Tan, X., &#38; Yang, J. (2024). Ergodicity of the underdamped mean-field Langevin dynamics. <i>Annals of Applied Probability</i>, <i>34</i>(3), 3181–3226. https://doi.org/10.1214/23-AAP2036</div> </div>
-
dc.identifier.issn
1050-5164
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/199053
-
dc.description.abstract
We study the long time behavior of an underdamped mean-field Langevin (MFL) equation, and provide a general convergence as well as an exponential convergence rate result under different conditions. The results on the MFL equation can be applied to study the convergence of the Hamiltonian gradient descent algorithm for the overparametrized optimization. We then provide some numerical examples of the algorithm to train a generative adversarial network (GAN).
en
dc.language.iso
en
-
dc.publisher
INST MATHEMATICAL STATISTICS-IMS
-
dc.relation.ispartof
Annals of Applied Probability
-
dc.subject
coupling
en
dc.subject
ergodicity
en
dc.subject
GAN
en
dc.subject
Underdamped mean-field Langevin dynamics
en
dc.title
Ergodicity of the underdamped mean-field Langevin dynamics
en
dc.type
Article
en
dc.type
Artikel
de
dc.identifier.scopus
2-s2.0-85196486488
-
dc.identifier.url
https://api.elsevier.com/content/abstract/scopus_id/85196486488
-
dc.contributor.affiliation
University of Paris-Saclay, France
-
dc.contributor.affiliation
Université Paris Dauphine-PSL, France
-
dc.contributor.affiliation
Chinese University of Hong Kong, China
-
dc.contributor.affiliation
TU Wien, Austria
-
dc.description.startpage
3181
-
dc.description.endpage
3226
-
dc.type.category
Original Research Article
-
tuw.container.volume
34
-
tuw.container.issue
3
-
tuw.journal.peerreviewed
true
-
tuw.peerreviewed
true
-
wb.publication.intCoWork
International Co-publication
-
tuw.researchTopic.id
A4
-
tuw.researchTopic.id
A3
-
tuw.researchTopic.name
Mathematical Methods in Economics
-
tuw.researchTopic.name
Fundamental Mathematics Research
-
tuw.researchTopic.value
50
-
tuw.researchTopic.value
50
-
dcterms.isPartOf.title
Annals of Applied Probability
-
tuw.publication.orgunit
E105 - Institut für Stochastik und Wirtschaftsmathematik
-
tuw.publisher.doi
10.1214/23-AAP2036
-
dc.date.onlinefirst
2024-06-11
-
dc.description.numberOfPages
46
-
tuw.author.orcid
0000-0001-5619-3540
-
tuw.author.orcid
0000-0002-4653-7730
-
wb.sci
true
-
wb.sciencebranch
Informatik
-
wb.sciencebranch
Wirtschaftswissenschaften
-
wb.sciencebranch
Mathematik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.oefos
5020
-
wb.sciencebranch.oefos
1010
-
wb.sciencebranch.value
10
-
wb.sciencebranch.value
20
-
wb.sciencebranch.value
70
-
item.cerifentitytype
Publications
-
item.languageiso639-1
en
-
item.fulltext
no Fulltext
-
item.openairetype
research article
-
item.openairecristype
http://purl.org/coar/resource_type/c_2df8fbb1
-
item.grantfulltext
none
-
crisitem.author.dept
Université Paris-Saclay
-
crisitem.author.dept
Universit� Paris Dauphine-PSL
-
crisitem.author.dept
Chinese University of Hong Kong
-
crisitem.author.dept
E105-05 - Forschungsbereich Stochastische Finanz- und Versicherungsmathematik
-
crisitem.author.orcid
0000-0001-5619-3540
-
crisitem.author.orcid
0000-0002-4653-7730
-
crisitem.author.parentorg
E105 - Institut für Stochastik und Wirtschaftsmathematik
-
Appears in Collections:
Article
Show simple item record

Google ScholarTM

Check