Convergence analysis of critical point regularization with non-convex regularizers

DOI10.1088/1361-6420/acdd8dzbMath1520.65035arXiv2207.14480MaRDI QIDQ6165998

Daniel Obmann, Markus Haltmeier

Publication date: 6 July 2023

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

Full work available at URL: https://arxiv.org/abs/2207.14480

zbMATH Keywords

regularizationneural networksinverse problemscritical pointsnon-convex regularizerlearned regularizerstability guarantees

Mathematics Subject Classification ID

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Variational methods in imaging
• Stability of the minimizers of least squares with a non-convex regularization. I: Local behavior
• Convexification-based globally convergent numerical method for a 1D coefficient inverse problem with experimental data
• Discretization of variational regularization in Banach spaces
• Generalized Bregman distances and convergence rates for non-convex regularization methods
• Sparse regularization with l ^q penalty term
• Generalized Gradients and Applications
• Analysis of bounded variation penalty methods for ill-posed problems
• NETT: solving inverse problems with deep neural networks

This page was built for publication: Convergence analysis of critical point regularization with non-convex regularizers