Save this video free

Lecture 6: Normalizing Flows 1 (KAIST CS479, Fall 2026)

Minhyuk Sung · 58:35 · 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 introduces normalizing flows as deterministic, invertible transformations from a simple latent prior to data, enabling exact likelihood evaluation through the change-of-variables formula. He derives the one- and multidimensional density corrections, explains the invertibility and Jacobian-computation challenges, and compares affine and elementwise monotonic transformations with the limitations each imposes.

Key takeaways

Chapters

0:00 VAE Latent Dimensions and the ELBO Training Objective
4:00 Interpreting the ELBO Through Joint Distributions
7:00 Why a Gaussian VAE Encoder Can Miss Complex Posteriors
9:30 Posterior Collapse and Misleading VAE Loss Curves
12:00 Autoregressive Models Versus VAEs for Generation
18:00 Normalizing Flows Replace Stochastic Decoding with an Invertible Map
22:00 Density Changes Under Stretching and the 1D Change of Variables
32:00 Invertibility Makes Exact 1D Likelihoods Possible
38:00 Multidimensional Flows Use the Jacobian Determinant
43:00 Worked Flow Example: Recovering z and Correcting the Density
49:00 Affine and Elementwise Monotonic Flow Designs

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

Transcript excerpt

0:01 So yeah let's continue discussing uh the so we discussed almost like everything about the last time like the only basic idea is that we are having this kind of the structure uh in terms of that we are defining some kind of the prior distribution the latent distribution and taking some kind of latent code first sampling from here and just mapping this to the data distribution uh by like the sampling from the another kind of the likelihood distribution that we are learning using the decoder, right? So that's kind of the basic thing. Uh but by the way, we didn't explicitly talk about this, but now when you think about kind of the dimension of the data distribution and also the latent distribution, should they have the same dimension uh for both of them? Uh not necessary, right? I mean it can

0:53 have some kind of different dimension for the data and the lat here. So as we also do some kind of the uh some bottleneck layer here in terms of having the the lower dimensional the space for the latent in the autoenccoder we can also set some kind of the lower dimensional space uh in the latent space especially like when you assume that the data distribution will have some kind of the some simpler the structure like know having some kind of the even in the higher dimensional space if the data will be placed in some kind of the lower dimension the subspace then we can easily basically reduce the dimension of the lat code here. So that's kind of thing. But actually you you need to keep this structure in mind because this structure is not only for the bae but also for the many other things also for the normalizing flow and g diffusion

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.