Ancestor Sampling for Particle Gibbs

We present a novel method in the family of particle MCMC methods that we refer to as particle Gibbs with ancestor sampling (PG-AS). Similarly to the existing PG with backward simulation (PG-BS) procedure, we use backward sampling to (considerably) improve the mixing of the PG kernel. Instead of using separate forward and backward sweeps as in PG-BS, however, we achieve the same effect in a single forward sweep. We apply the PG-AS framework to the challenging class of non-Markovian state-space models. We develop a truncation strategy of these models that is applicable in principle to any backward-simulation-based method, but which is particularly well suited to the PG-AS framework. In particular, as we show in a simulation study, PG-AS can yield an order-of-magnitude improved accuracy relative to PG-BS due to its robustness to the truncation error. Several application examples are discussed, including Rao-Blackwellized particle smoothing and inference in degenerate state-space models.

[1]  G. Bierman Fixed interval smoothing with discrete measurements , 1972 .

[2]  Jun S. Liu,et al.  Sequential importance sampling for nonparametric Bayes models: The next generation , 1999 .

[3]  M. Pitt,et al.  Filtering via Simulation: Auxiliary Particle Filters , 1999 .

[4]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[5]  Jun S. Liu,et al.  Mixture Kalman filters , 2000 .

[6]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[7]  Simon J. Godsill,et al.  Monte Carlo smoothing with application to audio signal enhancement , 2002, IEEE Trans. Signal Process..

[8]  A. Doucet,et al.  Monte Carlo Smoothing for Nonlinear Time Series , 2004, Journal of the American Statistical Association.

[9]  Paul Fearnhead,et al.  Particle filters for mixture models with an unknown number of components , 2004, Stat. Comput..

[10]  Branko Ristic,et al.  Beyond the Kalman Filter: Particle Filters for Tracking Applications , 2004 .

[11]  Branko Ristic,et al.  Bearings-Only Tracking of Manoeuvring Targets Using Particle Filters , 2004, EURASIP J. Adv. Signal Process..

[12]  Thomas B. Schön,et al.  Marginalized particle filters for mixed linear/nonlinear state-space models , 2005, IEEE Transactions on Signal Processing.

[13]  Yee Whye Teh,et al.  Bayesian Agglomerative Clustering with Coalescents , 2007, NIPS.

[14]  A. Doucet,et al.  A Tutorial on Particle Filtering and Smoothing: Fifteen years later , 2008 .

[15]  D. V. van Dyk,et al.  Partially Collapsed Gibbs Samplers , 2008 .

[16]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[17]  A. Doucet,et al.  Efficient Bayesian Inference for Switching State-Space Models using Discrete Particle Markov Chain Monte Carlo Methods , 2010, 1011.2437.

[18]  A. Doucet,et al.  Particle Markov chain Monte Carlo methods , 2010 .

[19]  Fredrik Lindsten,et al.  On the use of backward simulation in the particle Gibbs sampler , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[20]  S. Godsill,et al.  A Backward-Simulation Based Rao-Blackwellized Particle Smoother for Conditionally Linear Gaussian Models , 2012 .

[21]  Michael I. Jordan,et al.  Phylogenetic Inference via Sequential Monte Carlo , 2012, Systematic biology.