Continuous-discrete smoothing of diffusions
arXiv:1712.03807 · doi:10.1214/21-EJS1894
Abstract
Suppose X is a multivariate diffusion process that is observed discretely in time. At each observation time, a transformation of the state of the process is observed with noise. The smoothing problem consists of recovering the path of the process, consistent with the observations. We derive a novel Markov Chain Monte Carlo algorithm to sample from the exact smoothing distribution. The resulting algorithm is called the Backward Filtering Forward Guiding (BFFG) algorithm. We extend the algorithm to include parameter estimation. The proposed method relies on guided proposals introduced in Schauer et al. (2017). We illustrate its efficiency in a number of challenging problems.
arXiv commentRevised article with additional author Marcin Mider. Article contains an animated figure
References in corpus (11)
- Exact simulation of diffusions
- Guided proposals for simulating multi-dimensional diffusion bridges
- Reversible jump MCMC for nonparametric drift estimation for diffusion processes
- Bayesian estimation of discretely observed multi-dimensional diffusion processes using guided proposals
- A Geometric Framework for Stochastic Shape Analysis
- Controlled Sequential Monte Carlo
- Simulation of elliptic and hypo-elliptic conditional diffusions
- Bayesian estimation of incompletely observed diffusions
- Simulation of forward-reverse stochastic representations for conditional diffusions
- Automatic Backward Filtering Forward Guiding for Markov processes and graphical models
- On residual and guided proposals for diffusion bridge simulation
Cited by in corpus (6)
- A Geometric Framework for Stochastic Shape Analysis
- Control of Stochastic Quantum Dynamics by Differentiable Programming
- A piecewise deterministic Monte Carlo method for diffusion bridges
- Diffusion bridges for stochastic Hamiltonian systems and shape evolutions
- Automatic Backward Filtering Forward Guiding for Markov processes and graphical models
- Approximation of SPDE covariance operators by finite elements: A semigroup approach