Information spreading in diffusion models from effective field theory
Navonil Neogi ⋅ Nabil Iqbal
Abstract
We study score-matching diffusion models with a convolutional architecture. We argue that the inductive bias of locality means that the machinery of effective field theory from physics can be usefully applied to describe the denoising dynamics. As a simple application we study a toy example and show that the mutual information between two points grows in a manner predicted by a simple effective field theory.
Chat is not available.
Successful Page Load