Conditional particle filters with diffuse initial distributions

DOI10.1007/S11222-020-09975-1zbMATH Open1475.62041arXiv2006.14877OpenAlexW3135773817WikidataQ109284305 ScholiaQ109284305MaRDI QIDQ2058728FDOQ2058728

Authors: Santeri Karppinen, Matti Vihola 

Publication date: 9 December 2021

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Conditional particle filters (CPFs) are powerful smoothing algorithms for general nonlinear/non-Gaussian hidden Markov models. However, CPFs can be inefficient or difficult to apply with diffuse initial distributions, which are common in statistical applications. We propose a simple but generally applicable auxiliary variable method, which can be used together with the CPF in order to perform efficient inference with diffuse initial distributions. The method only requires simulatable Markov transitions that are reversible with respect to the initial distribution, which can be improper. We focus in particular on random-walk type transitions which are reversible with respect to a uniform initial distribution (on some domain), and autoregressive kernels for Gaussian initial distributions. We propose to use on-line adaptations within the methods. In the case of random-walk transition, our adaptations use the estimated covariance and acceptance rate adaptation, and we detail their theoretical validity. We tested our methods with a linear-Gaussian random-walk model, a stochastic volatility model, and a stochastic epidemic compartment model with time-varying transmission rate. The experimental findings demonstrate that our method works reliably with little user specification, and can be substantially better mixing than a direct particle Gibbs algorithm that treats initial states as parameters.

Full work available at URL: https://arxiv.org/abs/2006.14877

Recommendations

• Coupled conditional backward sampling particle filter
• FILTERING AND SMOOTHING IN STATE SPACE MODELS WITH PARTIALLY DIFFUSE INITIAL CONDITIONS
• Independent Particle Filters
• A uniformly convergent adaptive particle filter
• A note on auxiliary particle filters

zbMATH Keywords

Bayesian inferencesmoothingstate space modelhidden Markov modeladaptive Markov chain Monte Carlocompartment modelconditional particle filterdiffuse initialisation

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Cites Work

• Robust adaptive Metropolis algorithm with coerced acceptance rate
• Sequential Monte Carlo Samplers
• An adaptive Metropolis algorithm
• Particle Markov Chain Monte Carlo Methods
• On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
• On the stability and ergodicity of adaptive scaling Metropolis algorithms
• On the ergodicity properties of some adaptive MCMC algorithms
• Particle Gibbs with ancestor sampling
• Augmentation schemes for particle MCMC
• Time series analysis by state space methods.
• MCMC methods for functions: modifying old algorithms to make them faster
• Uniform ergodicity of the iterated conditional SMC and geometric ergodicity of particle Gibbs samplers
• On particle Gibbs sampling
• On disturbance state-space models and the particle marginal Metropolis-Hastings sampler
• The Asymptotic Efficiency of Simulation Estimators
• Coupled conditional backward sampling particle filter
• Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance

Cited In (2)

• Particle Filters for Multiscale Diffusions
• Coupled conditional backward sampling particle filter

This page was built for publication: Conditional particle filters with diffuse initial distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2058728)