Learning regularization functionals a supervised training approach

DOI10.1088/0266-5611/19/3/309zbMATH Open1046.90087OpenAlexW2062160197MaRDI QIDQ4407147FDOQ4407147

Authors: Luis Tenorio, Eldad Haber 

Publication date: 2 December 2003

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1088/0266-5611/19/3/309

Recommendations

• A machine learning approach to optimal Tikhonov regularization. I: Affine manifolds
• On regularization algorithms in learning theory
• A bilevel approach for parameter learning in inverse problems
• Data driven regularization by projection

Mathematics Subject Classification ID

Nonlinear programming (90C30) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical solution to inverse problems in abstract spaces (65J22)

Cited In (27)

• Preface for Inverse Problems special issue on learning and inverse problems
• DRIP: deep regularizers for inverse problems
• Learning semidefinite regularizers
• Partial differential equation regularization for supervised machine learning
• Estimating a Potential Without the Agony of the Partition Function
• Deep neural-network based optimization for the design of a multi-element surface magnet for MRI applications
• Learning spectral windowing parameters for regularization using unbiased predictive risk and generalized cross validation techniques for multiple data sets
• Bilevel Methods for Image Reconstruction
• A bilevel approach for parameter learning in inverse problems
• A general learning framework using local and global regularization
• Learning regularization parameters for general-form Tikhonov
• Bilevel parameter learning for higher-order total variation regularisation models
• A high order PDE-constrained optimization for the image denoising problem
• Limiting aspects of nonconvex \({TV}^{\phi}\) models
• A maximum a posteriori super resolution algorithm based on multidimensional Lorentzian distribution
• Learning regularization parameters of inverse problems via deep neural networks
• On spectral windows in supervised learning from data
• Optimising seismic imaging design parameters via bilevel learning
• Hybrid projection methods for large-scale inverse problems with mixed Gaussian priors
• The structure of optimal parameters for image restoration problems
• Modern regularization methods for inverse problems
• Example-based single document image super-resolution: a global MAP approach with outlier rejection
• Data driven regularization by projection
• Optimal selection of the regularization function in a weighted total variation model. II: Algorithm, its analysis and numerical tests
• Learning nonlocal regularization operators
• Solving inverse problems using data-driven models
• An optimal bilevel optimization model for the generalized total variation and anisotropic tensor parameters selection

This page was built for publication: Learning regularization functionals a supervised training approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4407147)