Journal
INVERSE PROBLEMS AND IMAGING
Volume 13, Issue 1, Pages 1-29Publisher
AMER INST MATHEMATICAL SCIENCES-AIMS
DOI: 10.3934/ipi.2019001
Keywords
Bayesian statistical estimation; inverse problems; Matern fields; hypermodels; convergence
Categories
Funding
- Engineering and Physical Sciences Research Council, United Kingdom (EPSRC) [EP/K034154/1]
- Academy of Finland [250215, 307741, 313709]
- Academy of Finland (AKA) [307741, 313709, 307741, 313709] Funding Source: Academy of Finland (AKA)
Ask authors/readers for more resources
We introduce non-stationary Matern field priors with stochastic partial differential equations, and construct correlation length-scaling with hyperpriors. We model both the hyperprior and the Matern prior as continuous-parameter random fields. As hypermodels, we use Cauchy and Gaussian random fields, which we map suitably to a desired correlation length-scaling range. For computations, we discretise the models with finite difference methods. We consider the convergence of the discretised prior and posterior to the discretisation limit. We apply the developed methodology to certain interpolation, numerical differentiation and deconvolution problems, and show numerically that we can make Bayesian inversion which promotes competing constraints of smoothness and edge-preservation. For computing the conditional mean estimator of the posterior distribution, we use a combination of Gibbs and Metropolis-within-Gibbs sampling algorithms.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available