Generative diffusion in very large dimensions

DOI10.1088/1742-5468/ACF8BAMaRDI QIDQ6607312zbMATH OpenFDO

Authors Giulio Biroli, Marc Mézard

Publication date 18 September 2024

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

Full work available at URL https://doi.org/10.1088/1742-5468/ACF8BA

zbMATH Keywords

diffusiongenerative modelsmachine learningstatistical physics

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Recommendations

• Deep Generative Models and Inverse Problems
• High-dimensional distribution generation through deep neural networks
• An introduction to deep generative modeling

Cites work

• A class of Wasserstein metrics for probability distributions
• Eigenvectors distribution and quantum unique ergodicity for deformed Wigner matrices
• Non-ergodic delocalization in the Rosenzweig-Porter model
• Reverse-time diffusion equation models

Cited in

(5)

• Replica symmetry breaking in supervised and unsupervised Hebbian networks
• Markov spin models for image generation: explicit large deviations with respect to the number of pixels
• Convergence properties of Markov models for image generation with applications to spin-flip dynamics and to diffusion processes
• Memorization and generalization in generative diffusion under the manifold hypothesis
• Cascade of phase transitions in the training of energy-based models

This page was built for publication: Generative diffusion in very large dimensions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6607312)