Inverse learning in Hilbert scales
arXiv:2002.10208 · doi:10.1007/s10994-022-06284-8
Abstract
We study the linear ill-posed inverse problem with noisy data in the statistical learning setting. Approximate reconstructions from random noisy data are sought with general regularization schemes in Hilbert scale. We discuss the rates of convergence for the regularized solution under the prior assumptions and a certain link condition. We express the error in terms of certain distance functions. For regression functions with smoothness given in terms of source conditions the error bound can then be explicitly established.
References in corpus (8)
- Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces
- Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
- Convergence analysis of Tikhonov regularization for non-linear statistical inverse learning problems
- Bayesian inverse problems with non-commuting operators
- Bayesian linear inverse problems in regularity scales
- Optimal rates for the regularized learning algorithms under general source condition
- Lepskii Principle in Supervised Learning
- Designing truncated priors for direct and inverse Bayesian problems