Simulation of forward-reverse stochastic representations for conditional diffusions
From MaRDI portal
Abstract: In this paper we derive stochastic representations for the finite dimensional distributions of a multidimensional diffusion on a fixed time interval, conditioned on the terminal state. The conditioning can be with respect to a fixed point or more generally with respect to some subset. The representations rely on a reverse process connected with the given (forward) diffusion as introduced in Milstein, Schoenmakers and Spokoiny [Bernoulli 10 (2004) 281-312] in the context of a forward-reverse transition density estimator. The corresponding Monte Carlo estimators have essentially root- accuracy, and hence they do not suffer from the curse of dimensionality. We provide a detailed convergence analysis and give a numerical example involving the realized variance in a stochastic volatility asset model conditioned on a fixed terminal value of the asset.
This paper develops a new approach for the simulation of conditional diffusion (diffusion bridges) expressed by the expectation of some function of a diffusion process given; it lies in some set at certain time points. The method is based on a forward-reverse estimator for a transition density. The corresponding Monte Carlo estimators are shown to have convergence based on detailed convergence analyses. Implementation issues are discussed based on truncated kernels and some numerical simulations are carried out including a stochastic volatility asset Heston model.
Recommendations
- Transition density estimation for stochastic differential equations via forward-reverse represen\-ta\-tions
- Simulation of Multivariate Diffusion Bridges
- Simulation of conditioned diffusion and application to parameter estimation
- Simple simulation of diffusion bridges with application to likelihood inference for diffusions
- Importance sampling techniques for estimation of diffusion models
Cites work
- Bounds for the fundamental solution of a parabolic equation
- Conditional path sampling for stochastic differential equations through drift relaxation
- Conditional path sampling of SDEs and the Langevin MCMC method
- Evaluation of conditional Wiener integrals by numerical integration of stochastic differential equations
- Forward and reverse representations for Markov chains
- scientific article; zbMATH DE number 3907496 (Why is no real title available?)
- scientific article; zbMATH DE number 1515832 (Why is no real title available?)
- Hypoelliptic non-homogeneous diffusions
- Importance sampling techniques for estimation of diffusion models
- MCMC METHODS FOR DIFFUSION BRIDGES
- On conditional diffusion processes
- On generating Monte Carlo samples of continuous diffusion bridges
- Retrospective exact simulation of diffusion sample paths with applications
- Sampling conditioned diffusions
- Sampling conditioned hypoelliptic diffusions
- Simple simulation of diffusion bridges with application to likelihood inference for diffusions
- Simulation of conditioned diffusion and application to parameter estimation
- Time reversal of diffusions
- Transition density estimation for stochastic differential equations via forward-reverse represen\-ta\-tions
- Two-particle models for the estimation of the mean and standard deviation of concentrations in coastal waters
Cited in
(13)- Transition density estimation for stochastic differential equations via forward-reverse represen\-ta\-tions
- Continuous-discrete smoothing of diffusions
- Forward and reverse representations for Markov chains
- Probability density estimation in stochastic environmental models using reverse representa\-tions
- An efficient forward-reverse expectation-maximization algorithm for statistical inference in stochastic reaction networks
- Simulation of elliptic and hypo-elliptic conditional diffusions
- Sequential Monte Carlo with Highly Informative Observations
- Forward or backward simulation? A comparative study
- Forward-reverse expectation-maximization algorithm for Markov chains: convergence and numerical analysis
- Multiscale modeling of wear degradation in cylinder liners
- An MM algorithm to estimate parameters in continuous-time Markov chains
- An efficient method to simulate diffusion bridges
- Simulation of conditioned diffusion and application to parameter estimation
This page was built for publication: Simulation of forward-reverse stochastic representations for conditional diffusions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q744383)
