Bayesian Linear Inverse Problems in Regularity Scales with Discrete Observations

Journal Article (2024)
Authors

Dong Yan (Student TU Delft)

S Gugushvili (Wageningen University & Research)

A. W. VAN DER VAART (TU Delft - Statistics)

Research Group
Statistics
Copyright
© 2024 Dong Yan, Shota Gugushvili, A.W. van der Vaart
To reference this document use:
https://doi.org/10.1007/s13171-024-00342-0
More Info
expand_more
Publication Year
2024
Language
English
Copyright
© 2024 Dong Yan, Shota Gugushvili, A.W. van der Vaart
Research Group
Statistics
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Issue number
Suppl 1
Volume number
86
Pages (from-to)
228-254
DOI:
https://doi.org/10.1007/s13171-024-00342-0
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

We obtain rates of contraction of posterior distributions in inverse problems with discrete observations. In a general setting of smoothness scales we derive abstract results for general priors, with contraction rates determined by discrete Galerkin approximation. The rate depends on the amount of prior concentration near the true function and the prior mass of functions with inferior Galerkin approximation. We apply the general result to non-conjugate series priors, showing that these priors give near optimal and adaptive recovery in some generality, Gaussian priors, and mixtures of Gaussian priors, where the latter are also shown to be near optimal and adaptive.

Files

S13171-024-00342-0.pdf
(pdf | 0.577 Mb)
- Embargo expired in 07-09-2024
License info not available