Geodesic
Sequential Bayesian inference for implicit hidden Markov models and current limitations
Pierre E. Jacob1
1 Department of Statistics, University of Oxford,
ESAIM. Proceedings, Tome 51 (2015), pp. 24-48 Cet article a éte moissonné depuis la source EDP Sciences

Voir la notice de l'article

Hidden Markov models can describe time series arising in various fields of science, by treating the data as noisy measurements of an arbitrarily complex Markov process. Sequential Monte Carlo (SMC) methods have become standard tools to estimate the hidden Markov process given the observations and a fixed parameter value. We review some of the recent developments allowing the inclusion of parameter uncertainty as well as model uncertainty. The shortcomings of the currently available methodology are emphasised from an algorithmic complexity perspective. The statistical objects of interest for time series analysis are illustrated on a toy “Lotka-Volterra” model used in population ecology. Some open challenges are discussed regarding the scalability of the reviewed methodology to longer time series, higher-dimensional state spaces and more flexible models.
DOI : 10.1051/proc/201551002

Pierre E. Jacob 1

1 Department of Statistics, University of Oxford, 
@article{EP_2015_51_a2,
     author = {Pierre E. Jacob},
     title = {Sequential {Bayesian} inference for implicit hidden {Markov} models and current limitations},
     journal = {ESAIM. Proceedings},
     pages = {24--48},
     year = {2015},
     volume = {51},
     doi = {10.1051/proc/201551002},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/201551002/}
}
TY  - JOUR
AU  - Pierre E. Jacob
TI  - Sequential Bayesian inference for implicit hidden Markov models and current limitations
JO  - ESAIM. Proceedings
PY  - 2015
SP  - 24
EP  - 48
VL  - 51
UR  - http://geodesic.mathdoc.fr/articles/10.1051/proc/201551002/
DO  - 10.1051/proc/201551002
LA  - en
ID  - EP_2015_51_a2
ER  - 
%0 Journal Article
%A Pierre E. Jacob
%T Sequential Bayesian inference for implicit hidden Markov models and current limitations
%J ESAIM. Proceedings
%D 2015
%P 24-48
%V 51
%U http://geodesic.mathdoc.fr/articles/10.1051/proc/201551002/
%R 10.1051/proc/201551002
%G en
%F EP_2015_51_a2
Pierre E. Jacob. Sequential Bayesian inference for implicit hidden Markov models and current limitations. ESAIM. Proceedings, Tome 51 (2015), pp. 24-48. doi: 10.1051/proc/201551002

Cité par Sources :