Why the noise model matters: a performance gap in learned regularization

DOI10.1088/1361-6420/AE3F4CMaRDI QIDQ6858128zbMATH OpenFDO

Authors Sebastian Banert, Christoph Brauer, Dirk A. Lorenz, Lionel Tondji

Publication date 13 February 2026

Published in Inverse Problems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1088/1361-6420/AE3F4C

zbMATH Keywords

Lavrentiev regularizationsupervised learningTikhonov regularizationvariational regularization

Mathematics Subject Classification ID

Numerical solution to inverse problems in abstract spaces (65J22) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Error estimates for joint Tikhonov and Lavrentiev regularization of constrained control problems
• scientific article; zbMATH DE number 432498 (Why is no real title available?)
• scientific article; zbMATH DE number 802915 (Why is no real title available?)
• Learning Variational Models with Unrolling and Bilevel Optimization
• NETT: solving inverse problems with deep neural networks
• On the method of Lavrentiev regularization for nonlinear ill-posed problems
• Solving ill-posed inverse problems using iterative deep neural networks
• Solving inverse problems using data-driven models
• The optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization

This page was built for publication: Why the noise model matters: a performance gap in learned regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6858128)