Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.
Mem- orization and generalization in generative diffusion under the manifold hypothesis.Journal of Statistical Mechanics: Theory and Experiment, 2025(7):073401, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An exact information theory of generalization phase transitions in Bayesian diffusion models
Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.