Dynamical Regimes of Diffusion Models

arXiv:2402.18491v1 Announce Type: new
Abstract: Using statistical physics methods, we study generative diffusion models in the regime where the dimension of space and the number of data are large, and the score function has been trained optimally. Our analysis reveals three distinct dynamical regimes during the backward generative diffusion process. The generative dynamics, starting from pure noise, encounters first a 'speciation' transition where the gross structure of data is unraveled, through a mechanism similar to symmetry breaking in phase transitions. …

abstract analysis arxiv cond-mat.stat-mech cs.lg data diffusion diffusion models dynamics function generative physics process space statistical study type