An Optimal Control Perspective on Diffusion-Based Generative Modeling
Offered By: Valence Labs via YouTube
Course Description
Overview
Explore an in-depth lecture on the connection between stochastic optimal control and generative models based on stochastic differential equations (SDEs). Delve into the derivation of a Hamilton-Jacobi-Bellman equation governing the evolution of log-densities of SDE marginals. Discover how this perspective allows for the transfer of methods from optimal control theory to generative modeling. Learn about the evidence lower bound as a consequence of the verification theorem from control theory. Examine a novel diffusion-based method for sampling from unnormalized densities, applicable to statistics and computational sciences. Follow along as the speaker covers topics such as SDE-based modeling, the Fokker-Planck equation, score matching, and compares Time Reversed Diffusion Sampler (DIS) with Path Integral Sampler (PIS). Engage with the Q&A session at the end to further understand this optimal control perspective on diffusion-based generative modeling.
Syllabus
- Intro
- The Task of Generative Modeling
- Overview of the Talk
- SDE-based Modeling
- The Fokker-Planck Equation
- Deriving the ELBO + Verification Theorem
- Denoting Score Matching
- Summary
- Time Reversed Diffusion Sampler DIS
- Path Integral Sampler PIS
- DIS vs. PIS
- Q+A
Taught by
Valence Labs
Related Courses
Path Integral Methods in Physics & FinanceIndian Institute of Technology Roorkee via Swayam Physics - Nonequilibrium Statistical Mechanics
NPTEL via YouTube Advanced statistical physics
École Polytechnique Fédérale de Lausanne via edX Introduction to Stochastic Modeling in Evolution - Lecture 1
International Centre for Theoretical Sciences via YouTube Entropy Method for Hypocoercive BGK and Fokker-Planck Equations
ICTP Mathematics via YouTube