Save this video free

Lecture 7: Normalizing Flows 2 (KAIST CS479, Fall 2026)

Minhyuk Sung · 1:00:53 · 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 develops normalizing flows as invertible, differentiable mappings from a D-dimensional Gaussian latent space to data, allowing exact likelihoods through the change-of-variables formula. He explains how coupling layers use triangular Jacobians for tractable determinants, then connects affine autoregressive flows to autoregressive density models and shows how stacking or reordering layers expands the distributions they can represent.

Key takeaways

Chapters

0:00 Normalizing Flows: Exact Likelihoods from Invertible Mappings
6:00 Composing Flow Layers and Accumulating Log-Determinants
16:00 Why Affine Layers Alone Cannot Build Expressive Flows
19:00 Coupling Layers Use Split Coordinates for Triangular Jacobians
26:00 Volume-Preserving Coupling and Its Nonlinear Transformations
35:00 Affine Coupling Adds Learned Scaling and Shifting
41:00 A Single Coupling Layer Limits Conditional Distributions
47:00 Stacking and Permuting Coupling Layers Expands Expressiveness
49:00 Autoregressive Flows Transform Coordinates Sequentially
53:00 Affine Autoregressive Flows Match Gaussian Autoregressive Models
57:00 Stacking Autoregressive Flows Enables Multimodal Slices
59:00 Flow Design Trade-Offs and Transition to GANs

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

Transcript excerpt

0:01 Okay, so let's continue discussing the normalizing flows. So, we started to discuss normalizing flows in the week before the the previous week. So, if I just briefly recap like what we discussed last time, so VAE was kind of the first model that we discussed as kind of the some latent developed model in a way that we first basically sample from the some simple distribution typically some Gaussian distribution in a kind of like latent space and then given that kind of sample we are mapping that into the real data point. So, that was kind of the typical way that so so many other kind of the models that we are also going to discuss would be following this kind of the concept. In terms of first defining some kind of

0:48 latent space and mapping the latent sample into the data point. So, the question is that how we are going to map this point, the point Z, into the real data point. So, VAE was kind of some sort of the stochastic model in terms of that given Z we are sampling the X, right? So, we are basically learning those kind of some conditional distribution. And the kind of the downside of the VAE was that we cannot directly compute the evidence. So, which means that we cannot simply basically perform the maximum likelihood estimation with that. So, in terms of that we basically define the elbow, the lower bound of the evidence in terms of maximizing the elbow, right? And we will actually get back to those kind of the concept of the elbow next time. But the here the basic idea of the

1:36 normalizing flow is that what if we can directly map this sample Z into the one of the real data point of

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.