Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings
SIAM/ASA Journal on Uncertainty Quantification · 31.03.2023 · 11 (1) · 91-138
DOI: 10.1137/21m1420927 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM/ASA Journal on Uncertainty Quantification, online erschienen am 03.03.2023. Verfasst von Juan P. Madrigal-Cianci und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: King Abdullah University of Science and Technology, Swiss Data Science Center, Alexander von Humboldt-Stiftung.
Abstract (Originalsprache)
In this work, we present, analyze, and implement a class of multilevel Markov chain Monte Carlo (ML-MCMC) algorithms based on independent Metropolis–Hastings proposals for Bayesian inverse problems. In this context, the likelihood function involves solving a complex differential model, which is then approximated on a sequence of increasingly accurate discretizations. The key point of this algorithm is to construct highly coupled Markov chains together with the standard multilevel Monte Carlo argument to obtain a better cost-tolerance complexity than a single-level MCMC algorithm. Our method extends the ideas of Dodwell et al., [ SIAM/ASA J. Uncertain. Quantif., 3 (2015), pp. 1075–1108] to a wider range of proposal distributions. We present a thorough convergence analysis of the ML-MCMC method proposed, and show, in particular, that (i) under some mild conditions on the (independent) proposals and the family of posteriors, there exists a unique invariant probability measure for the coupled chains generated by our method, and (ii) that such coupled chains are uniformly ergodic. We also generalize the cost-tolerance theorem of Dodwell et al. to our wider class of ML-MCMC algorithms. Finally, we propose a self-tuning continuation-type ML-MCMC algorithm. The presented method is tested on an array of academic examples, where some of our theoretical results are numerically verified. These numerical experiments evidence how our extended ML-MCMC method is robust when targeting some pathological posteriors, for which some of the previously proposed ML-MCMC algorithms fail.
Förderung
- King Abdullah University of Science and Technology
- Swiss Data Science Center
- Alexander von Humboldt-Stiftung
Zitieren
APA
Madrigal-Cianci, J. P., Nobile, F., & Tempone, R. (2023). Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings. SIAM/ASA Journal on Uncertainty Quantification, 11(1), 91-138. https://doi.org/10.1137/21m1420927
Vancouver
Madrigal-Cianci JP, Nobile F, Tempone R. Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings. SIAM/ASA Journal on Uncertainty Quantification. 2023;11(1):91-138. doi:10.1137/21m1420927
BibTeX
@article{MadrigalCianci2023,
author = {Madrigal-Cianci, Juan P. and Nobile, Fabio and Tempone, Raúl},
title = {Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings},
journal = {SIAM/ASA Journal on Uncertainty Quantification},
year = {2023},
volume = {11},
number = {1},
pages = {91--138},
doi = {10.1137/21m1420927}
}
EUVIMED