Save this video free

Lecture 4: Variational Autoencoders 1 (KAIST CS479, Fall 2026)

Minhyuk Sung · 1:03:20 · 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 variational autoencoders by contrasting autoregressive models with latent-variable generative models, where a prior and decoder generate data through an unobserved code. Because the evidence requires an intractable integral over latent variables, the lecture derives the evidence lower bound (ELBO) using an encoder to approximate the posterior, then interprets its reconstruction and KL-divergence terms and explains their trade-off.

Key takeaways

Chapters

0:00 Likelihood, Evidence, and Marginal Likelihood Depend on Perspective
5:23 Autoregressive Models Factorize Data into Conditional Distributions
7:49 KL Divergence Measures the NLL Cost of an Approximation
15:02 Gaussian KL Exercise and Nonnegativity
18:04 Convexity and Jensen's Inequality Prepare the ELBO Derivation
23:00 Latent Variables Turn Simple Sampling into Complex Data Generation
27:08 Standard Gaussian Priors and Bernoulli Image Decoders
31:29 Conditional Pixel Independence Does Not Mean Marginal Independence
34:40 Marginal Likelihood Is Intractable, and Monte Carlo Can Be Costly
42:15 An Encoder Approximates the Intractable Posterior
49:02 Jensen's Inequality Produces the Evidence Lower Bound
54:52 ELBO Reconstruction and KL Terms Trade Off Data Fit and Regularization

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

Transcript excerpt

0:00 it um uh actually before we get started some kind of a new topic actually one things that I wanted to quickly remind you is that uh did you have this kind of question like why we are using uh this term of the likelihood like all different ways uh because if we recall like what we discussed in the lecture two actually I mentioned this term of the likelihood twice in the two different kind of the parts of the slice Yes. So when you talked about the base rule like talking about the prior likelihood and also the evidence and also the posterior I I mentioned the term of the likelihood right uh that's the the case that we having this kind of the conditional distribution uh having the probability x conditioned by z right

0:49 and when you also talk about the maximum likelihood estimation uh for this the case that we are parameterizing uh the probability the density or the mass with the parameters the theta here I also mentioned this as kind of the likelihood uh did you see didn't you see this is kind like weird something or why we use like the same term like in different kind of context was it too clear to everyone or no one had that question I I expect that someone will going to basically raise up this question. No one will guess the this question. No actually we are using the term of the

1:39 likelihood in the same manner for both of the cases. So basically the meaning of the likelihood is basically we are seeing uh this kind of probability the density or the mass function as the function of the something. So basically when we fix the observation the x here uh this is now just becoming

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.