Save this video free

Lecture 10: Energy-Based Models 2 (KAIST CS479, Fall 2026)

Minhyuk Sung · 1:01:37 · Watch on YouTube

Part of KAIST AIC313/CS378. See all 12 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

Minhyuk Sung connects energy-based model sampling to stochastic differential equations (SDEs), using Brownian motion and the Fokker-Planck equation to explain how drift and noise jointly evolve probability densities. He shows that Langevin dynamics makes the target energy-based distribution stationary, distinguishes that property from convergence toward it, and relates continuous-time SDEs to practical discrete sampling updates.

Key takeaways

Chapters

0:00 Energy-Based Models: Sampling Without the Partition Function
4:00 Why Brownian Motion Matters for Diffusion Models
6:10 Brownian Motion: Gaussian Increments and Continuous Paths
10:00 From Noisy Sampling Updates to Stochastic Differential Equations
16:00 How an SDE Changes the Probability Distribution Over Time
19:40 Deriving the Fokker-Planck Drift Term with Probability Flow
34:40 Deriving the Fokker-Planck Diffusion Term from Gaussian Noise
44:30 Extending the Density Evolution Equation to Multiple Dimensions
47:00 Checking Langevin Dynamics with the Fokker-Planck Equation
51:00 Stationarity Is Not the Same as Convergence
55:15 Discretizing an SDE into Implementable Sampling Steps
59:00 Balancing Drift and Noise to Shape the Target Density

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:01 So if we briefly recap like what we discussed last time uh the idea basically the energy based model that we discussed last time was basically how we are going to basically model basically all the uh some kind of probability distribution using some kind of the energy function right so the idea of the GAN was basically classifying whether the of the data point is kind of real or the fake basically assign some kind of the binary value for that here the idea A was that we are not just assigning some kind of the binary kind of the classification uh the the output but actually assigning some kind of the one scalar the value which is the function here in a way that converting this into the probability density like this and this is kind of the way like how we define our some kind of the model in

0:49 terms like having those kind of form right so basically what we can see here is that as we have some kind of the lower the energy for the the data point X here that becomes like having some higher the the probability density right so in this way like what we discussed last time was basically to uh like learn those kind of the energy function uh using the maximum likelihood estimation like this way and how we can also sample based on this kind of the energy function right so those are basically two key ideas that we discussed last time so these are the case that the energy function can be given uh with some kind of the whatever some specificity application It can be the case that we are learning from some kind of the training data, right? And if we just try to learn those

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, Minhyuk Sung.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.