Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint

DOI10.1137/21M1450604zbMath1498.62067arXiv2109.11375OpenAlexW3199585919MaRDI QIDQ5052899

Paul Hagemann, Johannes Hertrich, Gabriele Drauschke

Publication date: 25 November 2022

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.11375

zbMATH Keywords

inverse problemsMarkov chain Monte Carloinvertible neural networks

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Monte Carlo methods (65C05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Numerical analysis or methods applied to Markov chains (65C40)

Related Items (3)

Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach ⋮ Reduced-order model-based variational inference with normalizing flows for Bayesian elliptic inverse problems ⋮ WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution

Uses Software

• Adam
• Glow
• nflows
• nsf
• sngan_projection
• SurVAE Flows

Cites Work

• Invertible neural networks versus MCMC for posterior reconstruction in grazing incidence X-ray fluorescence
• General state space Markov chains and MCMC algorithms
• Exponential convergence of Langevin distributions and their discrete approximations
• Iterative multiplicative filters for data labeling
• Bayesian Gaussian mixture linear inversion for geophysical inverse problems
• Brownian Motion, Martingales, and Stochastic Calculus
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Stabilizing Invertible Neural Networks Using Mixture Models
• BAYESIAN APPROACH TO THE STATISTICAL INVERSE PROBLEM OF SCATTEROMETRY: COMPARISON OF THREE SURROGATE MODELS
• On the convergence of the Metropolis-Hastings Markov chains
• Solving inverse problems using data-driven models
• Unnamed Item

This page was built for publication: Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint