Bayesian Inverse Problems
Preprint
Abstract
The posterior distribution in a nonparametric inverse problem is shown to contract to the true parameter at a rate that depends on the smoothness of the parameter, and the smoothness and scale of the prior. Correct combinations of these characteristics lead to the minimax rate. The frequentist coverage of credible sets is shown to depend on the combination of prior and true parameter, with smoother priors leading to zero coverage and rougher priors to conservative coverage. In the latter case credible sets are of the correct order of magnitude. The results are numerically illustrated by the problem of recovering a function from observation of a noisy version of its primitive.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Inverse problems: A Bayesian perspectiveActa Numerica, 2010
- Nonparametric statistical inverse problemsInverse Problems, 2008
- Regularization of some linear ill-posed problems with discretized random noisy dataMathematics of Computation, 2006
- Convergence rates of posterior distributionsThe Annals of Statistics, 2000
- Wald Lecture: On the Bernstein-von Mises theorem with infinite-dimensional parametersThe Annals of Statistics, 1999
- Statistical Inverse Estimation in Hilbert ScalesSIAM Journal on Applied Mathematics, 1996
- Statistical Estimation and Optimal RecoveryThe Annals of Statistics, 1994
- Renormalization Exponents and Optimal Pointwise Rates of ConvergenceThe Annals of Statistics, 1992
- Linear estimators and measurable linear transformations on a Hilbert spaceProbability Theory and Related Fields, 1984
- Generalized Inverses in Reproducing Kernel Spaces: An Approach to Regularization of Linear Operator EquationsSIAM Journal on Mathematical Analysis, 1974