What Inverse Problems Can Be Solved Using Neural Networks?

DOI10.48550/ARXIV.2610.19637MaRDI QIDQ7399399arXivFDO

Authors A. S. Leonov, D. V. Lukyanenko

Publication date 2026

Published in arXiv

Tldr We examine the relationship between classical and neural network methods for inverse problems. Neural networks can solve only conditionally well-posed problems due to violating Bakushinsky's veto from the theory of ill-posed problems.

Full work available at URL https://doi.org/10.48550/ARXIV.2610.19637

arXiv classification

math.NA

Cites work

• Let data talk: data-regularized operator learning theory for inverse problems
• Regularization of Inverse Problems
• Theoretical Perspectives on Deep Learning Methods in Inverse Problems

This page was built for publication: What Inverse Problems Can Be Solved Using Neural Networks?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7399399)