Skip to yearly menu bar Skip to main content


Tutorial
in
Tutorial: Harnessing Low Dimensionality in Diffusion Models: From Theory to Practice

Part I: Generalization of Learning Diffusion Models

[ ]
Mon 14 Jul 9:40 a.m. PDT — 10:25 a.m. PDT

Abstract:

We begin with an introduction to diffusion models, followed by a comprehensive study of their generalization: when and why they can learn low-dimensional target structures, how sample complexity scales with intrinsic data dimension, and how they transition from memorization to generalization. We also introduce a probability flow-based metric to quantify generalization and highlight several intriguing behaviors observed during training.

Chat is not available.