Learning regularization parameters of inverse problems via deep neural networks
From MaRDI portal
Publication:5157862
DOI10.1088/1361-6420/ac245dOpenAlexW3198331841MaRDI QIDQ5157862
Babak Maboudi Afkham, Julianne Chung, Matthias Chung
Publication date: 20 October 2021
Published in: Inverse Problems (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2104.06594
regularizationbilevel optimizationoptimal experimental designhyperparameter selectiondeep learningdeep neural networks
Related Items
Learning spectral windowing parameters for regularization using unbiased predictive risk and generalized cross validation techniques for multiple data sets ⋮ Numerical methods for CT reconstruction with unknown geometry parameters ⋮ A variable projection method for large-scale inverse problems with \(\ell^1\) regularization ⋮ Relaxation approach for learning neural network regularizers for a class of identification problems ⋮ DRIP: deep regularizers for inverse problems ⋮ Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling ⋮ Bilevel Methods for Image Reconstruction
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Nonlinear total variation based noise removal algorithms
- The Bayesian formulation of EIT: analysis and algorithms
- Bilevel parameter learning for higher-order total variation regularisation models
- Numerical methods for \(A\)-optimal designs with a sparsity constraint for ill-posed inverse problems
- A weighted-GCV method for Lanczos-hybrid regularization
- UPRE method for total variation parameter selection
- A bidiagonalization algorithm for solving large and sparse ill-posed systems of linear equations
- Multilayer feedforward networks are universal approximators
- Optimal filters from calibration data for image deconvolution with data acquisition error
- A GCV based method for nonlinear ill-posed problems
- Regularization by architecture: a deep prior approach for inverse problems
- Automated parameter selection for total variation minimization in image restoration
- \( \chi^2\) test for total variation regularization parameter selection
- AIR tools II: algebraic iterative reconstruction methods, improved implementation
- IR tools: a MATLAB package of iterative regularization methods and large-scale test problems
- The Mathematics of Computerized Tomography
- The Sample Average Approximation Method for Stochastic Discrete Optimization
- Generalized Arnoldi--Tikhonov Method for Sparse Reconstruction
- An Analysis of Infinite Dimensional Bayesian Inverse Shape Acoustic Scattering and Its Numerical Approximation
- Designing Optimal Spectral Filters for Inverse Problems
- Optimal Experimental Design for Inverse Problems with State Constraints
- A Fast Total Variation Minimization Method for Image Restoration
- Deblurring Images
- Numerical methods for experimental design of large-scale linear ill-posed inverse problems
- A Newton root-finding algorithm for estimating the regularization parameter for solving ill-conditioned least squares problems
- A Bidiagonalization-Regularization Procedure for Large Scale Discretizations of Ill-Posed Problems
- LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares
- Learning regularization functionals a supervised training approach
- Bilevel approaches for learning of variational imaging models
- Non-convergence of the L-curve regularization parameter selection method
- De-noising by soft-thresholding
- INVERSE ESTIMATION OF THE INITIAL CONDITION FOR THE HEAT EQUATION
- Bilevel optimization, deep learning and fractional Laplacian regularization with applications in tomography
- NETT: solving inverse problems with deep neural networks
- An inner–outer iterative method for edge preservation in image restoration and reconstruction *
- Solving inverse problems using data-driven models
- Flexible Krylov Methods for $\ell_p$ Regularization
- Optimal Design of Experiments
- Discrete Inverse Problems
- Numerical methods for the design of large-scale nonlinear discrete ill-posed inverse problems
- Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization
- An Introduction to Data Analysis and Uncertainty Quantification for Inverse Problems
- Parameter selection for total-variation-based image restoration using discrepancy principle
- Introduction to Bayesian Scientific Computing
- A Stochastic Approximation Method
- Approximation by superpositions of a sigmoidal function
