Rao-Blackwellized particle smoothers for conditionally linear Gaussian models

Abstract

Sequential Monte Carlo (SMC) methods, such as the particle filter, are by now one of the standard computational techniques for addressing the filtering problem in general state-space models. However, many applications require post-processing of data offline. In such scenarios the smoothing problem--in which all the available data is used to compute state estimates--is of central interest. We consider the smoothing problem for a class of conditionally linear Gaussian models. We present a forward-backward-type Rao-Blackwellized particle smoother (RBPS) that is able to exploit the tractable substructure present in these models. Akin to the well known Rao-Blackwellized particle filter, the proposed RBPS marginalizes out a conditionally tractable subset of state variables, effectively making use of SMC only for the "intractable part" of the model. Compared to existing RBPS, two key features of the proposed method are: (i) it does not require structural approximations of the model, and (ii) the aforementioned marginalization is done both in the forward direction and in the backward direction.

References in corpus (4)

• Sequential Monte Carlo smoothing with application to parameter estimation in non-linear state space models
• Sequential Monte Carlo smoothing for general state space hidden Markov models
• Efficient Bayesian Inference for Switching State-Space Models using Discrete Particle Markov Chain Monte Carlo Methods
• Identification of jump Markov linear models using particle filters

Cited by in corpus (6)

• Bayesian smoothing of dipoles in Magneto-/Electro-encephalography
• Particle rejuvenation of Rao-Blackwellized Sequential Monte Carlo smoothers for Conditionally Linear and Gaussian models
• Double Bayesian Smoothing as Message Passing
• Rao-Blackwellized Particle Smoothing as Message Passing
• A New Smoothing Technique based on the Parallel Concatenation of Forward/Backward Bayesian Filters: Turbo Smoothing
• Variational latent discrete representation for time series modelling