Non-Gaussian statistical inverse problems. Part II: Posterior convergence for approximated unknowns
Author:
Open Access
- 1 January 2012
- journal article
- Published by American Institute of Mathematical Sciences (AIMS) in Inverse Problems and Imaging
- Vol. 6 (2) , 267-287
Abstract
In practical statistical inverse problems, one often considers only finite-dimensional unknowns and investigates numerically their posterior probabilities. As many unknowns are function-valued, it is of interest to know whether the estimated probabilities converge when the finite-dimensional approximations of the unknown are refined. In this work, the generalized Bayes formula is shown to be a powerful tool in the convergence studies. With the help of the generalized Bayes formula, the question of convergence of the posterior distributions is returned to the convergence of the finite-dimensional (or any other) approximations of the unknown. The approach allows many prior distributions while the restrictions are mainly for the noise model and the direct theory. Three modes of convergence of posterior distributions are considered -- weak convergence, setwise convergence and convergence in variation. The convergence of conditional mean estimates is also studied.Keywords
This publication has 29 references indexed in Scilit:
- Approximation of Bayesian Inverse Problems for PDEsSIAM Journal on Numerical Analysis, 2010
- Bayesian inverse problems for functions and applications to fluid mechanicsInverse Problems, 2009
- Almost sure weak convergence of random probability measuresStochastics, 2006
- Two inequalities for conditional expectations and convergence results for filtersStatistics & Probability Letters, 2005
- Convergence results for conditional expectationsBernoulli, 2005
- Stochastic approximation properties in Banach spacesStudia Mathematica, 2003
- Convergence in Distribution of Conditional ExpectationsThe Annals of Probability, 1994
- Bayesian analysis in inverse problemsInverse Problems, 1991
- Convergence of Conditional ExpectationsThe Annals of Mathematical Statistics, 1971
- MONTE CARLO METHODS FOR SOLVING MULTIVARIABLE PROBLEMSAnnals of the New York Academy of Sciences, 1960