How regularization terms make invertible neural networks Bayesian point estimators

DOI10.1088/1361-6420/AE55C3MaRDI QIDQ7230419zbMATH OpenFDO

Authors

Publication date 17 April 2026

Published in Inverse Problems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1088/1361-6420/AE55C3

zbMATH Keywords

Bayesian inverse problemsinvertible neural networksregularization methods

Mathematics Subject Classification ID

Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical solution to inverse problems in abstract spaces (65J22) Artificial neural networks and deep learning (68T07)

Cites work

• A Stochastic Estimator of the Trace of the Influence Matrix for Laplacian Smoothing Splines
• Bayesian view on the training of invertible residual networks for solving linear inverse problems
• Deep learning
• Deep learning for trivial inverse problems
• Estimation of non-normalized statistical models by score matching
• Introduction to Bayesian Scientific Computing
• Invertible residual networks in the context of regularization theory for linear inverse problems
• Invertible ResNets for inverse imaging problems: competitive performance with provable regularization properties
• Modern regularization methods for inverse problems
• Semi-supervised invertible neural operators for Bayesian inverse problems
• Solving inverse problems using conditional invertible neural networks
• Solving inverse problems using data-driven models
• Tweedie’s Formula and Selection Bias

This page was built for publication: How regularization terms make invertible neural networks Bayesian point estimators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7230419)