EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accelerating Markov Chain Monte Carlo sampling with diffusion models

N.T. Hunt-Smith, W. Melnitchouk, F. Ringer, N. Sato, A.W. Thomas, M.J. White

Computer Physics Communications · 2024-03 · 296 · 109059

DOI: 10.1016/j.cpc.2023.109059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Physics Communications, 2024-03. Verfasst von N.T. Hunt-Smith und 5 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nuclear Physics, U.S. Department of Energy, Office of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Global fits of physics models require efficient methods for exploring high-dimensional and/or multimodal posterior functions. We introduce a novel method for accelerating Markov Chain Monte Carlo (MCMC) sampling by pairing a Metropolis-Hastings algorithm with a diffusion model that can draw global samples with the aim of approximating the posterior. We briefly review diffusion models in the context of image synthesis before providing a streamlined diffusion model tailored towards low-dimensional data arrays. We then present our adapted Metropolis-Hastings algorithm which combines local proposals with global proposals taken from a diffusion model that is regularly trained on the samples produced during the MCMC run. Our approach leads to a significant reduction in the number of likelihood evaluations required to obtain an accurate representation of the Bayesian posterior across several analytic functions, as well as for a physical example based on a global analysis of parton distribution functions. Our method is extensible to other MCMC techniques, and we briefly compare our method to similar approaches based on normalizing flows. A code implementation can be found at https://github.com/NickHunt-Smith/MCMC-diffusion.

Förderung

  • Nuclear Physics
  • U.S. Department of Energy
  • Office of Science

Zitieren

APA

Hunt-Smith, N., Melnitchouk, W., Ringer, F., Sato, N., Thomas, A., & White, M. (2024). Accelerating Markov Chain Monte Carlo sampling with diffusion models. Computer Physics Communications, 296, 109059. https://doi.org/10.1016/j.cpc.2023.109059

Vancouver

Hunt-Smith N, Melnitchouk W, Ringer F, Sato N, Thomas A, White M. Accelerating Markov Chain Monte Carlo sampling with diffusion models. Computer Physics Communications. 2024;296:109059. doi:10.1016/j.cpc.2023.109059

BibTeX
@article{HuntSmith2024,
  author = {Hunt-Smith, N.T. and Melnitchouk, W. and Ringer, F. and Sato, N. and Thomas, A.W. and White, M.J.},
  title = {Accelerating Markov Chain Monte Carlo sampling with diffusion models},
  journal = {Computer Physics Communications},
  year = {2024},
  volume = {296},
  pages = {109059},
  doi = {10.1016/j.cpc.2023.109059}
}
Kostenlos starten →