Back to Search
Start Over
Divide-and-Conquer with Sequential Monte Carlo
- Source :
- Journal of Computational and Graphical Statistics, 26(2):445-458, 2017
- Publication Year :
- 2014
-
Abstract
- We propose a novel class of Sequential Monte Carlo (SMC) algorithms, appropriate for inference in probabilistic graphical models. This class of algorithms adopts a divide-and-conquer approach based upon an auxiliary tree-structured decomposition of the model of interest, turning the overall inferential task into a collection of recursively solved sub-problems. The proposed method is applicable to a broad class of probabilistic graphical models, including models with loops. Unlike a standard SMC sampler, the proposed Divide-and-Conquer SMC employs multiple independent populations of weighted particles, which are resampled, merged, and propagated as the method progresses. We illustrate empirically that this approach can outperform standard methods in terms of the accuracy of the posterior expectation and marginal likelihood approximations. Divide-and-Conquer SMC also opens up novel parallel implementation options and the possibility of concentrating the computational effort on the most challenging sub-problems. We demonstrate its performance on a Markov random field and on a hierarchical logistic regression problem.
- Subjects :
- Statistics - Computation
Statistics - Machine Learning
Subjects
Details
- Database :
- arXiv
- Journal :
- Journal of Computational and Graphical Statistics, 26(2):445-458, 2017
- Publication Type :
- Report
- Accession number :
- edsarx.1406.4993
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1080/10618600.2016.1237363