Diffusion models suffer critical slowing down when sampling near criticality in the O(n) model but deeper local architectures reduce training-time scaling from quadratic to logarithmic in system size.
(14) with the Fourier space kernel in Eq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.dis-nn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The critical slowing down in diffusion models
Diffusion models suffer critical slowing down when sampling near criticality in the O(n) model but deeper local architectures reduce training-time scaling from quadratic to logarithmic in system size.