An O(log2 N) SMC2 Algorithm on Distributed Memory with an Approx. Optimal L-Kernel

Calibrating statistical models using Bayesian inference often requires both accurate and timely estimates of parameters of interest. Particle Markov Chain Monte Carlo (p-MCMC) and Sequential Monte Carlo Squared (SMC²) are two methods that use an unbiased estimate of the log-likelihood obtained from a particle filter (PF) to evaluate the target distribution. P-MCMC constructs a single Markov chain which is sequential by nature so cannot be readily parallelized using Distributed Memory (DM) architectures. This is in contrast to SMC² which includes processes, such as importance sampling, that are described as embarrassingly parallel. However, difficulties arise when attempting to parallelize resampling. None-the-less, the choice of backward kernel, recycling scheme and compatibility with DM architectures makes SMC² an attractive option when compared with p-MCMC. In this paper, we present an SMC² framework that includes the following features: an optimal (in terms of time complexity) $\mathcal{O}(\log_2 N)$ parallelization for DM architectures, an approximately optimal (in terms of accuracy) backward kernel, and an efficient recycling scheme. On a cluster of 128 DM processors, the results on a biomedical application show that SMC² achieves up to a 70× speed-up vs its sequential implementation. It is also more accurate and roughly 54× faster than p-MCMC. A GitHub link is given which provides access to the code.