Variational regularization in inverse problems and machine learning
From MaRDI portal
Abstract: This paper discusses basic results and recent developments on variational regularization methods, as developed for inverse problems. In a typical setup we review basic properties needed to obtain a convergent regularization scheme and further discuss the derivation of quantitative estimates respectively needed ingredients such as Bregman distances for convex functionals. In addition to the approach developed for inverse problems we will also discuss variational regularization in machine learning and work out some connections to the classical regularization theory. In particular we will discuss a reinterpretation of machine learning problems in the framework of regularization theory and a reinterpretation of variational methods for inverse problems in the framework of risk minimization. Moreover, we establish some previously unknown connections between error estimates in Bregman distances and generalization errors.
Summary: This paper discusses basic results and recent developments on variational regularization methods, as developed for inverse problems. In a typical setup we review basic properties needed to obtain a convergent regularization scheme and further discuss the derivation of quantitative estimates respectively the needed ingredients such as Bregman distances for convex functionals. In addition to the approach developed for inverse problems, we will also discuss variational regularization in machine learning and work out some connections to the classical regularization theory. In particular we will discuss a reinterpretation of machine learning problems in the framework of regularization theory and a reinterpretation of variational methods for inverse problems in the framework of risk minimization. Moreover, we establish some previously unknown connections between error estimates in Bregman distances and generalization errors. For the entire collection see [Zbl 1519.00033].
Recommendations
- Learned regularizers for inverse problems
- Regularization graphs -- a unified framework for variational regularization of inverse problems
- Variational regularisation for inverse problems with imperfect forward operators and general noise models
- Modern regularization methods for inverse problems
- Variational regularization of inverse problems for manifold-valued data
Cites work
- A convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators
- A guide to the TV zoo
- A mollifier method for linear operator equations of the first kind
- A New Approach to Source Conditions in Regularization with General Residual Term
- An introduction to the mathematical theory of inverse problems
- An Iterative Regularization Method for Total Variation-Based Image Restoration
- Analysis of regularized inversion of data corrupted by white Gaussian noise
- Approximate inverse for linear and some nonlinear problems
- Bias reduction in variational regularization
- Characterizations of variational source conditions, converse results, and maxisets of spectral regularization methods
- CLEAR: covariant least-square refitting with applications to image restoration
- Convergence analysis of (statistical) inverse problems under conditional stability estimates
- Convergence rates of convex variational regularization
- Convergence Rates of General Regularization Methods for Statistical Inverse Problems and Applications
- Error estimates for general fidelities
- Error estimates for non-quadratic regularization and the relation to enhancement
- Error estimation for Bregman iterations and inverse scale space methods in image restoration
- scientific article; zbMATH DE number 3551792 (Why is no real title available?)
- scientific article; zbMATH DE number 1376935 (Why is no real title available?)
- scientific article; zbMATH DE number 1865939 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- scientific article; zbMATH DE number 3241900 (Why is no real title available?)
- Inverse problems in spaces of measures
- Iterative methods for nonlinear ill-posed problems in Banach spaces: convergence and applications to parameter identification problems
- Large noise in variational regularization
- Linear convergence rates for Tikhonov regularization with positively homogeneous functionals
- Modern regularization methods for inverse problems
- Parameter choice in Banach space regularization under variational inequalities
- Proximal Minimization Methods with Generalized Bregman Functions
- Regularization of ill-posed problems in Banach spaces: convergence rates
- Solving inverse problems using data-driven models
- Sparse recovery in inverse problems
- Support recovery for sparse super-resolution of positive measures
- The Discontinuity Set of Solutions of the TV Denoising Problem and Some Extensions
- The mathematics of computerized tomography
- The Random Feature Model for Input-Output Maps between Banach Spaces
- Training neural networks with noisy data as an ill-posed problem
- Variational inequalities and higher order convergence rates for Tikhonov regularisation on Banach spaces
- Variational smoothness assumptions in convergence rate theory -- an overview
- Variational source conditions and conditional stability estimates for inverse problems in PDEs
- Well posedness and convergence of some regularisation methods for non-linear ill posed problems
Cited in
(7)- Regularization by architecture: a deep prior approach for inverse problems
- A Generative Variational Model for Inverse Problems in Imaging
- Variational regularisation for inverse problems with imperfect forward operators and general noise models
- Variance-based regularization with convex objectives
- From kernel methods to neural networks: a unifying variational formulation
- Hierarchical Bayesian inverse problems: a high-dimensional statistics viewpoint
- Optimal linear baseline models for scientific machine learning
This page was built for publication: Variational regularization in inverse problems and machine learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6064560)
