Geodesic
Non-linear Markov Chain Monte Carlo
Christophe Andrieu1 ; Ajay Jasra2 ; Arnaud Doucet3 ; Pierre Del Moral4
1 Department of Mathematics, University of Bristol, UK
2 Department of Mathematics, Imperial College London, UK
3 Departments of Statistics & Computer Science, University of British Columbia, CA
4 Department of Mathematics, University of Nice Sophia Antipolis, FR
ESAIM. Proceedings, Tome 19 (2007), pp. 79-84 Cet article a éte moissonné depuis la source EDP Sciences

Voir la notice de l'article

In this paper we introduce a class of non-linear Markov Chain Monte Carlo (MCMC) methods for simulating from a probability measure π. Non-linear Markov kernels (e.g. Del Moral (2004)) can be constructed to admit π as an invariant distribution and have typically superior mixing properties to ordinary (linear) MCMC kernels. However, such non-linear kernels often cannot be simulated exactly, so, in the spirit of particle approximations of Feynman-Kac formulae (Del Moral 2004), we construct approximations of the non-linear kernels via Self-Interacting Markov Chains (Del Moral Miclo, Proc. R. Soc. Lond. A, 460, 325-46, 2004.) (SIMC). We present several non-linear kernels and investigate the performance of our approximations with some simulations.
DOI : 10.1051/proc:071911

Christophe Andrieu 1 ; Ajay Jasra 2 ; Arnaud Doucet 3 ; Pierre Del Moral 4

1 Department of Mathematics, University of Bristol, UK
2 Department of Mathematics, Imperial College London, UK
3 Departments of Statistics & Computer Science, University of British Columbia, CA
4 Department of Mathematics, University of Nice Sophia Antipolis, FR 
@article{EP_2007_19_a11,
     author = {Christophe Andrieu and Ajay Jasra and Arnaud Doucet and Pierre Del Moral},
     title = {Non-linear {Markov} {Chain} {Monte} {Carlo}},
     journal = {ESAIM. Proceedings},
     pages = {79--84},
     year = {2007},
     volume = {19},
     doi = {10.1051/proc:071911},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1051/proc:071911/}
}
TY  - JOUR
AU  - Christophe Andrieu
AU  - Ajay Jasra
AU  - Arnaud Doucet
AU  - Pierre Del Moral
TI  - Non-linear Markov Chain Monte Carlo
JO  - ESAIM. Proceedings
PY  - 2007
SP  - 79
EP  - 84
VL  - 19
UR  - http://geodesic.mathdoc.fr/articles/10.1051/proc:071911/
DO  - 10.1051/proc:071911
LA  - en
ID  - EP_2007_19_a11
ER  - 
%0 Journal Article
%A Christophe Andrieu
%A Ajay Jasra
%A Arnaud Doucet
%A Pierre Del Moral
%T Non-linear Markov Chain Monte Carlo
%J ESAIM. Proceedings
%D 2007
%P 79-84
%V 19
%U http://geodesic.mathdoc.fr/articles/10.1051/proc:071911/
%R 10.1051/proc:071911
%G en
%F EP_2007_19_a11
Christophe Andrieu; Ajay Jasra; Arnaud Doucet; Pierre Del Moral. Non-linear Markov Chain Monte Carlo. ESAIM. Proceedings, Tome 19 (2007), pp. 79-84. doi: 10.1051/proc:071911

Cité par Sources :