Bayesian Posterior Contraction Rates for Linear Severely Ill-posed Inverse Problems
arXiv:1210.1563 · doi:10.1515/jip-2012-0071
Abstract
We consider a class of linear ill-posed inverse problems arising from inversion of a compact operator with singular values which decay exponentially to zero. We adopt a Bayesian approach, assuming a Gaussian prior on the unknown function. If the observational noise is assumed to be Gaussian then this prior is conjugate to the likelihood so that the posterior distribution is also Gaussian. We study Bayesian posterior consistency in the small observational noise limit. We assume that the forward operator and the prior and noise covariance operators commute with one another. We show how, for given smoothness assumptions on the truth, the scale parameter of the prior can be adjusted to optimize the rate of posterior contraction to the truth, and we explicitly compute the logarithmic rate.
25 pages, 2 figures
References in corpus (2)
Cited by in corpus (13)
- On the well-posedness of Bayesian inverse problems
- Posterior Consistency for Bayesian Inverse Problems through Stability and Regression Results
- Sparsity-promoting and edge-preserving maximum a posteriori estimators in non-parametric Bayesian inverse problems
- Convergence Rates for Learning Linear Operators from Noisy Data
- Posterior consistency and convergence rates for Bayesian inversion with hypoelliptic operators
- On the Bernstein-Von Mises Theorem for High Dimensional Nonlinear Bayesian Inverse Problems
- Importance Sampling: Intrinsic Dimension and Computational Cost
- Bayesian inverse problems with unknown operators
- Designing truncated priors for direct and inverse Bayesian problems
- Consistency of the posterior distribution in generalised linear inverse problems
- Preconditioning the prior to overcome saturation in Bayesian inverse problems
- Analysis of the Gibbs sampler for hierarchical inverse problems
- Some results on contraction rates for Bayesian inverse problems