EUVIMEDEUVIMED entdecken
Crossref

Explicit convergence bounds for Metropolis Markov chains: Isoperimetry, spectral gaps and profiles

Christophe Andrieu, Anthony Lee, Sam Power, Andi Q. Wang

The Annals of Applied Probability · 01.08.2024 · 34 (4) · 4022-4071

DOI: 10.1214/24-aap2058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Annals of Applied Probability, erschienen am 01.08.2024. Verfasst von Christophe Andrieu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 62 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We derive the first explicit bounds for the spectral gap of a random walk Metropolis algorithm on Rd for any value of the proposal variance, which when scaled appropriately recovers the correct d−1 dependence on dimension for suitably regular invariant distributions. We also obtain explicit bounds on the L2-mixing time for a broad class of models. In obtaining these results, we refine the use of isoperimetric profile inequalities to obtain conductance profile bounds, which also enable the derivation of explicit bounds in a much broader class of models. We also obtain similar results for the preconditioned Crank–Nicolson Markov chain, obtaining dimension-independent bounds under suitable assumptions.

Zitieren

APA

Andrieu, C., Lee, A., Power, S., & Wang, A. Q. (2024). Explicit convergence bounds for Metropolis Markov chains: Isoperimetry, spectral gaps and profiles. The Annals of Applied Probability, 34(4), 4022-4071. https://doi.org/10.1214/24-aap2058

Vancouver

Andrieu C, Lee A, Power S, Wang AQ. Explicit convergence bounds for Metropolis Markov chains: Isoperimetry, spectral gaps and profiles. The Annals of Applied Probability. 2024;34(4):4022-4071. doi:10.1214/24-aap2058

BibTeX
@article{Andrieu2024,
  author = {Andrieu, Christophe and Lee, Anthony and Power, Sam and Wang, Andi Q.},
  title = {Explicit convergence bounds for Metropolis Markov chains: Isoperimetry, spectral gaps and profiles},
  journal = {The Annals of Applied Probability},
  year = {2024},
  volume = {34},
  number = {4},
  pages = {4022--4071},
  doi = {10.1214/24-aap2058}
}
Kostenlos starten →