Convergence of Denoising Diffusion Models Under the Manifold Hypothesis
Offered By: Alan Turing Institute via YouTube
Course Description
Overview
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.
Syllabus
Convergence of denoising diffusion models under the manifold hypothesis
Taught by
Alan Turing Institute
Related Courses
Visual Recognition & UnderstandingUniversity at Buffalo via Coursera Deep Learning for Computer Vision
IIT Hyderabad via Swayam Deep Learning in Life Sciences - Spring 2021
Massachusetts Institute of Technology via YouTube Advanced Deep Learning Methods for Healthcare
University of Illinois at Urbana-Champaign via Coursera Generative Models
Serrano.Academy via YouTube