Regularization of inverse problems: deep equilibrium models versus bilevel learning

DOI10.3934/NACO.2023026MaRDI QIDQ6952983zbMATH OpenFDO

Authors Danilo Riccio, Matthias J. Ehrhardt, Martin Benning

Publication date 25 July 2025

Published in Numerical Algebra, Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/NACO.2023026

zbMATH Keywords

bilevel learningbilevel optimizationdeep equilibriumdeep learninginverse problemsregularizationvariational regularization

Mathematics Subject Classification ID

Linear operators and ill-posed problems, regularization (47A52) Iterative procedures involving nonlinear operators (47J25) Fixed-point iterations (47J26) Inverse problems in optimal control (49N45) Differential geometry of symmetric spaces (53C35) Numerical optimization and variational techniques (65K10)

Cites work

• A bilevel optimization approach for parameter learning in variational models
• Anderson acceleration for fixed-point iterations
• Bilevel Methods for Image Reconstruction
• Bilevel optimization with nonsmooth lower level problems
• Bilevel parameter learning for higher-order total variation regularisation models
• Convex analysis and monotone operator theory in Hilbert spaces
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Feasibility-based fixed point networks
• Fields of experts
• First-order methods in optimization
• Fixed Point Strategies in Data Science
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• scientific article; zbMATH DE number 3192366 (Why is no real title available?)
• Image denoising: learning the noise model via nonsmooth PDE-constrained optimization
• Inexact derivative-free optimization for bilevel learning
• Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
• Mathematical methods in image reconstruction
• Modern regularization methods for inverse problems
• Nonlinear total variation based noise removal algorithms
• Partial differential equation methods for image inpainting
• Proximité et dualité dans un espace hilbertien
• Solving ill-posed inverse problems using iterative deep neural networks
• The structure of optimal parameters for image restoration problems
• Variational methods in imaging

This page was built for publication: Regularization of inverse problems: deep equilibrium models versus bilevel learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6952983)