Duan, L. and Farmer, C. L. and Moroz, I. M. (2010) Regularized particle filter with Langevin resampling step. In: ICNAAM 2010. (Submitted)

PDF
99kB 
Abstract
The solution of an inverse problem involves the estimation of variables and parameters values given by the statespace system. While a general (infinitedimensional) optimal filter theory [1, 2] exists for nonlinear systems with Gaussian or nonGaussian noise, applications rely on (finitedimensional) suboptimal approximations to the optimal filter for practical implementations. The most widelystudied filters of this kind include the Regularized Particle Filter (RPF) [3, 4] and the Ensemble Square Root Filter (EnSRF) [5]. The latter is an adhoc approximation to the Bayes Filter, while the former is rigorously formulated, based upon the GlivenkoCantelli theorem. By introducing a new global resampling step to the RPF, the EnSRF is proved to approximate the RPF in a special case.
Item Type:  Conference or Workshop Item (Paper) 

Subjects:  D  G > General 
Research Groups:  Oxford Centre for Collaborative Applied Mathematics 
ID Code:  1004 
Deposited By:  Peter Hudston 
Deposited On:  28 Oct 2010 13:40 
Last Modified:  29 May 2015 18:41 
Repository Staff Only: item control page