Augmented pseudo-marginal Metropolis-Hastings for partially observed diffusion processes
From MaRDI portal
Publication:2114055
DOI10.1007/S11222-022-10083-5zbMATH Open1482.62011arXiv2009.05318OpenAlexW3086712597MaRDI QIDQ2114055FDOQ2114055
Andrew Golightly, Chris Sherlock
Publication date: 14 March 2022
Published in: Statistics and Computing (Search for Journal in Brave)
Abstract: We consider the problem of inference for nonlinear, multivariate diffusion processes, satisfying It^o stochastic differential equations (SDEs), using data at discrete times that may be incomplete and subject to measurement error. Our starting point is a state-of-the-art correlated pseudo-marginal Metropolis-Hastings algorithm, that uses correlated particle filters to induce strong and positive correlation between successive likelihood estimates. However, unless the measurement error or the dimension of the SDE is small, correlation can be eroded by the resampling steps in the particle filter. We therefore propose a novel augmentation scheme, that allows for conditioning on values of the latent process at the observation times, completely avoiding the need for resampling steps. We integrate over the uncertainty at the observation times with an additional Gibbs step. Connections between the resulting pseudo-marginal scheme and existing inference schemes for diffusion processes are made, giving a unified inference framework that encompasses Gibbs sampling and pseudo marginal schemes. The methodology is applied in three examples of increasing complexity. We find that our approach offers substantial increases in overall efficiency, compared to competing methods.
Full work available at URL: https://arxiv.org/abs/2009.05318
Bayesian inferencedata augmentationstochastic differential equationlinear noise approximationpseudo-marginal Metropolis-Hastings
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Bayesian estimation of discretely observed multi-dimensional diffusion processes using guided proposals
- Guided proposals for simulating multi-dimensional diffusion bridges
- The pseudo-marginal approach for efficient Monte Carlo computations
- Particle Markov Chain Monte Carlo Methods
- Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator
- Scalable inference for Markov processes with intractable likelihoods
- Particle approximations of the score and observed information matrix in state space models with application to parameter estimation
- The Correlated Pseudo-Marginal Method
- Normal forms for reduced stochastic climate models
- On the efficiency of pseudo-marginal random walk Metropolis algorithms
- Particle Markov Chain Monte Carlo for Efficient Numerical Simulation
- Augmentation schemes for particle MCMC
- On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
- Bayesian inference for nonlinear multivariate diffusion models observed with error
- Markov chain Monte Carlo inference for Markov jump processes via the linear noise approximation
- Inference for reaction networks using the linear noise approximation
- Bayesian Inference for Stochastic Kinetic Models Using a Diffusion Approximation
- On inference for partially observed nonlinear diffusion models using the Metropolis-Hastings algorithm
- The parabolic differential equations and the associated semigroups of transformation
- A lognormal central limit theorem for particle approximations of normalizing constants
- Inference for stochastic volatility models using time change transformations
- Inference for Diffusion Processes
- Bayesian inference for Heston-STAR models
- An MCMC Algorithm for Parameter Estimation in Signals with Hidden Intermittent Instability
- Correlated pseudo-marginal schemes for time-discretised stochastic kinetic models
- Bayesian inference for irreducible diffusion processes using the pseudo-marginal approach
- Improved bridge constructs for stochastic differential equations
Cited In (2)
Uses Software
This page was built for publication: Augmented pseudo-marginal Metropolis-Hastings for partially observed diffusion processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2114055)
