Communications in Mathematical Sciences

Volume 2 (2004)

Number 4

Conditional Path Sampling of SDEs and the Langevin MCMC Method

Pages: 685 – 697

(Fast Communication)

DOI: http://dx.doi.org/10.4310/CMS.2004.v2.n4.a7

Authors

Andrew M. Stuart

Jochen Voss

Petter Wilberg

Abstract

We introduce a stochastic PDE based approach to sampling paths of SDEs, conditional on observations. The SPDEs are derived by generalising the Langevin MCMC method to infinite dimensions. Various applications are described, including sampling paths subject to two end-point conditions (bridges) and nonlinear filter/smoothers.

Full Text (PDF format)