Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method

DOI10.1088/1361-6420/acc2b6OpenAlexW4323660577MaRDI QIDQ5886392

Unnamed Author, Wenbin Li, Davide Bianchi

Publication date: 5 April 2023

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

Full work available at URL: https://arxiv.org/abs/2210.03314

zbMATH Keywords

U-netdata-driven regularizeriterated network Tikhonovregularization of inverse problemuniformly convex neural networks

Mathematics Subject Classification ID

Numerical analysis (65-XX) Miscellaneous topics in partial differential equations (35Rxx)

Uses Software

• Adam
• U-Net

Cites Work

• Unnamed Item
• Unnamed Item
• On nondecreasing sequences of regularization parameters for nonstationary iterated Tikhonov
• Variational methods in imaging
• On the choice of the regularization parameter for iterated Tikhonov regularization of ill-posed problems
• Nonstationary iterated Tikhonov regularization
• Limitations of the \(L\)-curve method in ill-posed problems
• Old and new parameter choice rules for discrete ill-posed problems
• A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms
• On generalized iterated Tikhonov regularization with operator-dependent seminorms
• Nonstationary iterated Tikhonov regularization in Banach spaces with uniformly convex penalty terms
• On Orlicz sequence spaces. II
• Graph Laplacian for image deblurring
• Regularization Preconditioners for Frame-Based Image Deblurring with Reduced Boundary Artifacts
• Nonstationary iterated Tikhonov regularization for ill-posed problems in Banach spaces
• Nonlocal Operators with Applications to Image Processing
• Uniformly convex functions on Banach spaces
• Iterative total variation schemes for nonlinear inverse problems
• Analysis of Discrete Ill-Posed Problems by Means of the L-Curve
• Variational Analysis
• Deep learning for photoacoustic tomography from sparse data
• A stochastic gradient descent approach with partitioned-truncated singular value decomposition for large-scale inverse problems of magnetic modulus data
• NETT: solving inverse problems with deep neural networks
• Modulus-based iterative methods for constrained ℓ _p – ℓ _q minimization
• Deep synthesis network for regularizing inverse problems
• Deep unfolding of a proximal interior point method for image restoration
• Solving inverse problems using data-driven models
• Deep Learning: An Introduction for Applied Mathematicians
• Iterated fractional Tikhonov regularization
• Iterated Tikhonov regularization with a general penalty term
• An Iterative Regularization Method for Total Variation-Based Image Restoration
• On uniformly convex functions

This page was built for publication: Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method