On free energy barriers in Gaussian priors and failure of cold start MCMC for high-dimensional unimodal distributions

We exhibit examples of high-dimensional unimodal posterior distributions arising in nonlinear regression models with Gaussian process priors for which Markov chain Monte Carlo (MCMC) methods can take an exponential run-time to enter the regions where the bulk of the posterior measure concentrates. O...

Descripción completa

Detalles Bibliográficos
Autores principales: Bandeira, Afonso S., Maillard, Antoine, Nickl, Richard, Wang, Sven
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society 2023
Materias:
Articles
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10041355/
https://www.ncbi.nlm.nih.gov/pubmed/36970818
http://dx.doi.org/10.1098/rsta.2022.0150

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10041355/
https://www.ncbi.nlm.nih.gov/pubmed/36970818
http://dx.doi.org/10.1098/rsta.2022.0150

Ejemplares similares