Gauss-Newton method for solving linear inverse problems with neural network coders

DOI10.1007/s43670-023-00066-6zbMath1520.65036arXiv2303.14058OpenAlexW4385580083MaRDI QIDQ6049832

Otmar Scherzer, Bernd Hofmann, Zuhair Nashed

Publication date: 18 September 2023

Published in: Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2303.14058

zbMATH Keywords

neural networksinverse problemsGauss-Newton method

Mathematics Subject Classification ID

Iterative procedures involving nonlinear operators (47J25) Numerical solutions to equations with nonlinear operators (65J15) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items

Quadratic Neural Networks for Solving Inverse Problems

Cites Work

• Regularization methods in Banach spaces.
• Iterative regularization methods for nonlinear ill-posed problems
• Variational methods in imaging
• A Kantorovich-type convergence analysis for the Gauss-Newton-method
• Convergence of Newton-like methods for singular operator equations using outer inverses
• On ill-posedness measures and space change in Sobolev scales
• Multilayer feedforward networks are universal approximators
• A convergence analysis of the Landweber iteration for nonlinear ill-posed problems
• Discretization of variational regularization in Banach spaces
• Convergence Rates for Newton’s Method at Singular Points
• Inner, outer, and generalized inverses in banach and hilbert spaces
• Asymptotic Mesh Independence of Newton–Galerkin Methods via a Refined Mysovskii Theorem
• Affine Invariant Convergence Theorems for Newton’s Method and Extensions to Related Methods
• Regularization in state space
• On autoconvolution and regularization
• Factors influencing the ill-posedness of nonlinear problems
• On the degree of ill-posedness for nonlinear problems
• On the nature of ill-posedness of an inverse problem arising in option pricing
• Optimization Methods for Large-Scale Machine Learning
• Data Driven Reconstruction Using Frames and Riesz Bases
• Data driven regularization by projection
• Deep synthesis network for regularizing inverse problems
• A convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators
• The Newton-Kantorovich Theorem
• Approximation by superpositions of a sigmoidal function
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item