H 2 Markov Chain Monte Carlo Methods - Part 1

Auteurs : Robert, Christian P. (Auteur de la Conférence)
CIRM (Editeur )

Loading the player...
Metropolis-Hastings algorithm Markov chains random walk geometric ergodicity reversible jump Langevin diffusion discretization optimal scale for random walk Gibbs sampler counter example: lack of convergence slice sampler convergence of the Gibbs sampler Hammersley-Clifford theorem Rao-Blackwellization danger of improper priors adaptive MCMC questions of the audience

Résumé : In this short course, we recall the basics of Markov chain Monte Carlo (Gibbs & Metropolis sampelrs) along with the most recent developments like Hamiltonian Monte Carlo, Rao-Blackwellisation, divide & conquer strategies, pseudo-marginal and other noisy versions. We also cover the specific approximate method of ABC that is currently used in many fields to handle complex models in manageable conditions, from the original motivation in population genetics to the several reinterpretations of the approach found in the recent literature. Time allowing, we will also comment on the programming developments like BUGS, STAN and Anglican that stemmed from those specific algorithms.

Codes MSC :
60J10 - Markov chains (discrete-time Markov processes on discrete state spaces)
62F15 - Bayesian inference
65C05 - Monte Carlo methods
65C40 - Computational Markov chains (numerical analysis)

    Informations sur la Vidéo

    Langue : Anglais
    Date de publication : 16/03/16
    Date de captation : 29/02/16
    Collection : Research talks ; Probability and Statistics
    Format : MP4 (.mp4) - HD
    Durée : 01:05:32
    Domaine : Probability & Statistics
    Audience : Doctorants , Post - Doctorants ; Chercheurs
    Download : https://videos.cirm-math.fr/2016-02-29_Robert.mp4

Informations sur la rencontre

Nom de la rencontre : Thematic month on statistics - Week 5: Bayesian statistics and algorithms / Mois thématique sur les statistiques - Semaine 5 : Semaine Bayésienne et algorithmes
Organisateurs de la rencontre : Le Gouic, Thibaut ; Pommeret, Denys ; Willer, Thomas
Dates : 29/02/2016 - 04/03/16
Année de la rencontre : 2016
URL Congrès : http://conferences.cirm-math.fr/1619.html

Citation Data

DOI : 10.24350/CIRM.V.18936903
Cite this video as: Robert, Christian P. (2016). Markov Chain Monte Carlo Methods - Part 1. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.18936903
URI : http://dx.doi.org/10.24350/CIRM.V.18936903

Voir aussi


Titres de périodiques et e-books électroniques (Depuis le CIRM)

Ressources Electroniques

Books & Print journals

Recherche avancée