Geometric regularity in deterministic sampling dynamics of diffusion-based generative models

DOI10.1088/1742-5468/AE17ACMaRDI QIDQ7293904zbMATH OpenFDO

Authors Defang Chen, Zhenyu Zhou, Can Wang, Siwei Lyu

Publication date 10 July 2026

Published in Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1088/1742-5468/AE17AC

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites work

• A Connection Between Score Matching and Denoising Autoencoders
• A generalized solution of the orthogonal Procrustes problem
• An Automatic Method of Solving Discrete Programming Problems
• Applied stochastic differential equations
• Convergence of score-based generative modeling for general data distributions
• Differentiable manifolds
• Differential geometry of curves and surfaces. With a new preface by the author
• Estimation of non-normalized statistical models by score matching
• Generative diffusion in very large dimensions
• High dimensional random walks can appear low dimensional: application to influenza H3N2 evolution
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 3124366 (Why is no real title available?)
• scientific article; zbMATH DE number 6159604 (Why is no real title available?)
• scientific article; zbMATH DE number 3256958 (Why is no real title available?)
• scientific article; zbMATH DE number 3059227 (Why is no real title available?)
• scientific article; zbMATH DE number 7646025 (Why is no real title available?)
• Large-scale inference. Empirical Bayes methods for estimation, testing, and prediction
• Least squares estimation without priors or supervision
• Memorization and generalization in generative diffusion under the manifold hypothesis
• Parametric Empirical Bayes Inference: Theory and Applications
• Reverse-time diffusion equation models
• Spontaneous symmetry breaking in generative diffusion models
• The estimation of the gradient of a density function, with applications in pattern recognition
• What regularized auto-encoders learn from the data-generating distribution

This page was built for publication: Geometric regularity in deterministic sampling dynamics of diffusion-based generative models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7293904)