Bayesian inverse problems with heterogeneous variance
From MaRDI portal
Publication:6049784
Abstract: We consider inverse problems in Hilbert spaces under correlated Gaussian noise and use a Bayesian approach to find their regularised solution. We focus on mildly ill-posed inverse problems with the noise being generalised derivative of fractional Brownian motion, using a novel wavelet - based approach we call vaguelette-vaguelette. It allows us to apply sequence space methods without assuming that all operators are simultaneously diagonalisable. The results are proved for more general bases and covariance operators. Our primary aim is to study the posterior contraction rate in such inverse problems over Sobolev classes of true functions, comparing it to the derived minimax rate. Secondly, we study the effect of plugging in a consistent estimator of variances in sequence space on the posterior contraction rate, for instance where there are repeated observations. This result is also applied to the problem where the forward operator is observed with error. Thirdly, we show that an adaptive empirical Bayes posterior distribution contracts at the optimal rate, in the minimax sense, under a condition on prior smoothness, with a plugged in maximum marginal likelihood estimator of the prior scale. These theoretical results are illustrated on simulated data.
Cites work
- A general approach to posterior contraction in nonparametric inverse problems
- Adaptive estimation for inverse problems with noisy operators
- Asymptotic equivalence for regression under fractional noise
- Bayes procedures for adaptive inference in inverse problems for the white noise model
- Bayesian inverse problems for functions and applications to fluid mechanics
- Bayesian inverse problems with Gaussian priors
- Bayesian inverse problems with non-conjugate priors
- Besov priors for Bayesian inverse problems
- Coherent Bayesian analysis of inspiral signals
- Consistency of the posterior distribution in generalized linear inverse problems
- Convergence rates of posterior distributions.
- Empirical Bayes scaling of Gaussian priors in the white noise model
- scientific article; zbMATH DE number 3712239 (Why is no real title available?)
- scientific article; zbMATH DE number 1313655 (Why is no real title available?)
- scientific article; zbMATH DE number 1085990 (Why is no real title available?)
- scientific article; zbMATH DE number 2169747 (Why is no real title available?)
- scientific article; zbMATH DE number 3444248 (Why is no real title available?)
- scientific article; zbMATH DE number 910674 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- Inverse problems with structural prior information
- Model reduction and pollution source identification from remote sensing data
- Multiscale decompositions on bounded domains
- Nonlinear estimation for linear inverse problems with error in the operator
- Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
- Nonparametric statistical inverse problems
- Normal approximation and concentration of spectral projectors of sample covariance
- On coverage and local radial rates of credible sets
- On minimax filtering over ellipsoids
- Optimal series representation of fractional Brownian sheets
- Optimality of an explicit series expansion of the fractional Brownian sheet
- Posterior contraction in Bayesian inverse problems under Gaussian priors
- Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
- Rate optimality of wavelet series approximations of fractional Brownian motion
- Rates of contraction of posterior distributions based on \(p\)-exponential priors
- Regularizing priors for linear inverse problems
- Representation formulae for the fractional Brownian motion
- The wavelet-based synthesis for fractional Brownian motion proposed by F. Sellan and Y. Meyer: Remarks and fast implementation
- Wavelet decomposition approaches to statistical inverse problems
- Wavelets, generalized white noise and fractional integration: The synthesis of fractional Brownian motion
Cited in
(3)
This page was built for publication: Bayesian inverse problems with heterogeneous variance
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6049784)
