DAWN-FM: data-aware and noise-informed flow matching for solving inverse problems

DOI10.3934/FODS.2026005MaRDI QIDQ7294458zbMATH OpenFDO

Authors Shadab Ahamed, Eldad Haber

Publication date 13 July 2026

Published in Foundations of Data Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/FODS.2026005

Mathematics Subject Classification ID

Numerical solutions to stochastic differential and integral equations (65C30) 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

• An over complete deep learning method for inverse problems
• Conditional Wasserstein distances with applications in Bayesian OT flow matching
• Data analysis tools for uncertainty quantification of inverse problems
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Distributed Tikhonov regularization for ill-posed inverse problems from a Bayesian perspective
• DRIP: deep regularizers for inverse problems
• Likelihood-free inference by ratio estimation
• Priorconditioners for linear systems
• Solving ill-posed inverse problems using iterative deep neural networks
• Solving inverse problems using conditional invertible neural networks
• Statistical and computational inverse problems.
• Theory-guided auto-encoder for surrogate construction and inverse modeling
• Variational methods in imaging

This page was built for publication: DAWN-FM: data-aware and noise-informed flow matching for solving inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7294458)