Invertible neural networks versus MCMC for posterior reconstruction in grazing incidence X-ray fluorescence

DOI10.1007/978-3-030-75549-2_42MaRDI QIDQ826224zbMATH OpenOpenAlexFDO

Authors Anna Andrle, Nando Farchmin, Paul Hagemann, Sebastian Heidenreich, Victor Soltwisch, Gabriele Steidl

Publication date 20 December 2021

Full work available at URL https://arxiv.org/abs/2102.03189

zbMATH Keywords

MCMCinverse problemBayesian inversionGIXRFinvertible neural networkstransport maps

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Artificial neural networks and deep learning (68T07) Computer science (68-XX)

Cites work

• scientific article; zbMATH DE number 1022658 (Why is no real title available?)
• An introduction to MCMC for machine learning
• Stabilizing Invertible Neural Networks Using Mixture Models

Cited in

(4)

• Stochastic normalizing flows for inverse problems: a Markov chains viewpoint
• A dimension-reduced variational approach for solving physics-based inverse problems using generative adversarial network priors and normalizing flows
• Learning from small data sets: patch-based regularizers in inverse problems for image reconstruction
• WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution

This page was built for publication: Invertible neural networks versus MCMC for posterior reconstruction in grazing incidence X-ray fluorescence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q826224)