Gradient flow in energy-based models for strictly positive binary distributions produces stable data-consistent fixed points and a learning hierarchy that favors lower-order interactions first, mechanistically explaining distributional simplicity bias.
A theory of learning data statistics in diffusion models, from easy to hard
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Diffusion models require new generalization frameworks because memorization and novel generation are incompatible, so research should focus on what models learn before memorization begins.
citing papers explorer
-
Distributional simplicity bias and effective convexity in Energy Based Models
Gradient flow in energy-based models for strictly positive binary distributions produces stable data-consistent fixed points and a learning hierarchy that favors lower-order interactions first, mechanistically explaining distributional simplicity bias.
-
Understanding diffusion models requires rethinking (again) generalization
Diffusion models require new generalization frameworks because memorization and novel generation are incompatible, so research should focus on what models learn before memorization begins.