Deep-plug-and-play proximal Gauss-Newton method with applications to nonlinear, ill-posed inverse problems

DOI10.3934/ipi.2023014MaRDI QIDQ6115633

Francesco Colibazzi, Andrea Samoré, Serena Morigi, Damiana Lazzaro

Publication date: 10 August 2023

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

zbMATH Keywords

nonlinear optimizationill-posed inverse problemsgraph neural networksdeep-PnPproximal Gauss-Newton

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Cites Work

• The Little Engine that Could: Regularization by Denoising (RED)
• A new median formula with applications to PDE based denoising
• Convergence analysis of a proximal Gauss-Newton method
• Regularisation of neural networks by enforcing Lipschitz continuity
• Learning nonlinear electrical impedance tomography
• Spatially-adaptive variational reconstructions for linear inverse electrical impedance tomography
• Non-convex total variation regularization for convex denoising of signals
• A proximal iteratively regularized Gauss-Newton method for nonlinear inverse problems
• Proximal Newton-Type Methods for Minimizing Composite Functions
• A regularizing Levenberg - Marquardt scheme, with applications to inverse groundwater filtration problems
• Convex Image Denoising via Non-Convex Regularization
• Image denoising using scale mixtures of gaussians in the wavelet domain
• Existence and Uniqueness for Electrode Models for Electric Current Computed Tomography
• Image Restoration by Iterative Denoising and Backward Projections
• Relaxed Gauss--Newton Methods with Applications to Electrical Impedance Tomography
• Plug-and-Play Unplugged: Optimization-Free Reconstruction Using Consensus Equilibrium
• On Quasi-Newton Forward-Backward Splitting: Proximal Calculus and Convergence
• Signal Recovery by Proximal Forward-Backward Splitting
• Tikhonov replacement functionals for iteratively solving nonlinear operator equations

This page was built for publication: Deep-plug-and-play proximal Gauss-Newton method with applications to nonlinear, ill-posed inverse problems