Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Neural SDEs - Deep Generative Models in the Diffusion Limit - Maxim Raginsky

Institute for Advanced Study via YouTube

Overview

Explore the diffusion limit of deep generative models in this comprehensive lecture. Delve into the unified perspective on sampling and variational inference through stochastic control. Learn how to quantify the expressiveness of diffusion-based generative models and discover efficient sampling techniques for a wide class of terminal target distributions. Examine the proof of sampling accuracy using Kullback-Leibler divergence and investigate an unbiased, finite-variance simulation scheme implementable as a deep generative model with a random number of layers. Cover topics such as continuous-time neural nets, parabolic PDEs, optimal control, the Schrödinger Bridge Problem, and nonparametric sampling, while gaining insights into empirical process techniques.

Syllabus

Introduction
What is a generative model
Diffusion process
Continuoustime neural nets
Questions
Coming up
Exact Sampling
Parabolic PDEs
Optimal Control
Schroedinger Bridge Problem
Variational Inference
Nonparametric Sampling
Proof
Empirical Process Techniques

Taught by

Institute for Advanced Study

Reviews

Start your review of Neural SDEs - Deep Generative Models in the Diffusion Limit - Maxim Raginsky

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.