Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The forward–backward envelope for sampling with the overdamped Langevin algorithm
Umeå University, Faculty of Science and Technology, Department of Mathematics and Mathematical Statistics.
Maxwell Institute for Mathematical Sciences, Bayes Centre, Edinburgh, United Kingdom; School of Mathematics, University of Edinburgh, Edinburgh, United Kingdom.
Maxwell Institute for Mathematical Sciences, Bayes Centre, Edinburgh, United Kingdom; School of Mathematics, University of Edinburgh, Edinburgh, United Kingdom.
2023 (English)In: Statistics and computing, ISSN 0960-3174, E-ISSN 1573-1375, Vol. 33, no 4, article id 85Article in journal (Refereed) Published
Abstract [en]

In this paper, we analyse a proximal method based on the idea of forward–backward splitting for sampling from distributions with densities that are not necessarily smooth. In particular, we study the non-asymptotic properties of the Euler–Maruyama discretization of the Langevin equation, where the forward–backward envelope is used to deal with the non-smooth part of the dynamics. An advantage of this envelope, when compared to widely-used Moreu–Yoshida one and the MYULA algorithm, is that it maintains the MAP estimator of the original non-smooth distribution. We also study a number of numerical experiments that support our theoretical findings.

Place, publisher, year, edition, pages
Springer Nature, 2023. Vol. 33, no 4, article id 85
Keywords [en]
Convex optimization, Langevin equation, Markov chain Monte Carlo
National Category
Probability Theory and Statistics Computational Mathematics
Identifiers
URN: urn:nbn:se:umu:diva-209544DOI: 10.1007/s11222-023-10254-yISI: 000999342700002Scopus ID: 2-s2.0-85160908171OAI: oai:DiVA.org:umu-209544DiVA, id: diva2:1766536
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Knut and Alice Wallenberg FoundationAvailable from: 2023-06-13 Created: 2023-06-13 Last updated: 2023-09-05Bibliographically approved

Open Access in DiVA

fulltext(1036 kB)89 downloads
File information
File name FULLTEXT01.pdfFile size 1036 kBChecksum SHA-512
39792689489be5a6bdc1a8eac77f1fa38acc32fefb3618f13ae078452bc0489ec698802749caedc186e0b9048061b36dbef54d7fcb0ba5f74b5ddf7ecccda7ba
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Eftekhari, Armin

Search in DiVA

By author/editor
Eftekhari, Armin
By organisation
Department of Mathematics and Mathematical Statistics
In the same journal
Statistics and computing
Probability Theory and StatisticsComputational Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 89 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 189 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf