Diffusion models on the Gaussian O(n) model exhibit critical slowing down with shallow networks that deeper local score approximations can reduce to logarithmic training-time scaling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.dis-nn 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The critical slowing down in diffusion models
Diffusion models on the Gaussian O(n) model exhibit critical slowing down with shallow networks that deeper local score approximations can reduce to logarithmic training-time scaling.