Divide-and-Conquer with Sequential Monte Carlo

We develop a Sequential Monte Carlo (SMC) procedure for inference in probabilistic graphical models using the divide-and-conquer methodology. The method is based on an auxiliary tree-structured decomposition of the model of interest turning the overall inferential task into a collection of recursively solved sub-problems. Unlike a standard SMC sampler, the proposed method 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 estimation accuracy. It also opens up novel parallel implementation options and the possibility of concentrating the computational effort on the most challenging sub-problems. The proposed method is applicable to a broad class of probabilistic graphical models. We demonstrate its performance on a Markov random field and on a hierarchical Bayesian model.