Normalizing flow sampling with Langevin dynamics in the latent space

DOI10.1007/S10994-024-06623-XMaRDI QIDQ7006560zbMATH OpenFDO

Authors Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais

Publication date 28 March 2025

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S10994-024-06623-X

zbMATH Keywords

generative modelsMetropolis adjusted Langevin algorithmMonte Carlo samplingnormalizing flows

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A multivariate Kolmogorov-Smirnov test of goodness of fit
• A taste of topology
• Adaptive Monte Carlo augmented with normalizing flows
• High-dimensional Gaussian sampling: a review and a unifying approach based on a stochastic proximal point algorithm
• scientific article; zbMATH DE number 646825 (Why is no real title available?)
• Langevin diffusions and the Metropolis-adjusted Langevin algorithm
• Normalizing flows for probabilistic modeling and inference
• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• Real Analysis and Probability
• Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
• Stabilizing Invertible Neural Networks Using Mixture Models
• Stochastic differential equations. An introduction with applications.
• The Gaussian double-bubble and multi-bubble conjectures

This page was built for publication: Normalizing flow sampling with Langevin dynamics in the latent space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7006560)