arXiv Machine Learning
Information Spreading in Diffusion Models from Effective Field Theory
Read the original on arXiv Machine Learning →The paper investigates score‑matching diffusion models that use a convolutional architecture, arguing that their locality bias allows effective field theory from physics to describe denoising dynamics. The authors first apply this framework to a toy example with an analytical solution, then to MNIST, demonstrating that in both settings the mutual information between two points increases as predicted by a simple effective field theory of Brownian motion.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.