PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Gaussian Process Approximations of Stochastic Differential Equations
Cedric Archambeau, Dan Cornford, Manfred Opper and John Shawe-Taylor
In: Gaussian Process In Practice, 12-13 June 2006, Bletchley Park, UK.

There is a more recent version of this eprint available. Click here to view it.


Stochastic differential equations arise naturally in a range of contexts, from financial to environmental modelling. Current solution methods are based on a range of strong and weak approximation techniques, however these are limited in their representation of the posterior process in the presence of data. In this work we present a novel Gaussian process approximation to the posterior measure over paths for a general class of stochastic differential equations in the presence of observations. The method is applied to two simple problems: the Ornstein-Uhlenbeck process, of which the exact solution is known and can be compared to, and the double-well system, for which standard approaches such as the ensemble Kalman smoother fail to provide a satisfactory result. Experiments show that our variational approximation is viable and that the results are very promising as the variational approximation outperforms standard Gaussian process regression for non-Gaussian Markov processes.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:2374
Deposited By:Cedric Archambeau
Deposited On:22 November 2006

Available Versions of this Item