Explore the theoretical foundations of denoising diffusion models in this 46-minute lecture by Valentin de Bortoli from CNRS, France. Delve into the convergence analysis of these state-of-the-art generative models for image and audio synthesis, focusing on scenarios where the target distribution is supported on a lower-dimensional manifold or given by an empirical distribution. Examine quantitative bounds on the Wasserstein distance between the target data distribution and the generative distribution of diffusion models. Gain insights into the theoretical underpinnings of these models, addressing limitations in current approaches that assume target density admits a density with respect to the Lebesgue measure.
Convergence of Denoising Diffusion Models Under the Manifold Hypothesis
Alan Turing Institute via YouTube
Overview
Syllabus
Convergence of denoising diffusion models under the manifold hypothesis
Taught by
Alan Turing Institute
Related Courses
-
From Denoising Diffusion Models to Transport for Generative Modeling and Inference
-
Denoising Diffusion Models for Denoising Diffusion MRI - Tiange Xiang
-
Denoising Diffusion Probabilistic Models and Generative Moment Matching Networks - Lecture 17
-
Manifold Diffusion Fields - Learning Generative Models of Continuous Functions on Riemannian Manifolds
-
Diffusion Models and Score-Based Generative Models Explained - From Scratch
-
Deep Generative Models and Stable Diffusion: Revolution in Visual Synthesis - Lecture by Björn Ommer
