Save this video free

Lecture 5: Variational Autoencoders 2 (KAIST CS479, Fall 2026)

Minhyuk Sung · 1:02:22 · 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 explains how variational autoencoders optimize the evidence lower bound (ELBO) using a reconstruction term and a KL-divergence regularizer, with Gaussian assumptions making the KL term analytically tractable. He connects the objective to encoder and decoder design, reconstruction losses, the reparameterization trick, and the tradeoff between faithful reconstruction and useful generation, including posterior collapse and β-VAE weighting.

Key takeaways

Chapters

0:00 Why VAEs Use Gaussian Distributions and the ELBO
6:48 The Encoder's Role in Training Versus Generation
9:18 Bayes Rule Quiz: From Prior to Posterior
13:01 Gaussian Approximate Posteriors and Encoder Outputs
18:45 Decoder Likelihoods: Binary Cross-Entropy and Squared Error
25:09 Estimating Reconstruction Loss with Latent Samples
28:25 Closed-Form KL Regularization for a Diagonal Gaussian
33:10 Reconstruction and KL Terms Pull Latent Codes in Opposite Directions
38:26 Backpropagating Through VAE Sampling
43:15 VAE Training, Generation, and the Autoencoder Comparison
48:07 β-VAE Weighting and Posterior Collapse
55:31 Posterior Overlap, Blurry Outputs, and Generative Tradeoffs

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

Transcript excerpt

0:01 Yeah. So yeah, we discussed the K divergence last time and the most important thing in the discussion of the BA would be is that how we can really compute this KD divergence especially for the cases like when the these two distributions are defined as the Gaus and the distribution. Obviously for the other distributions we might want to know how we can compute this. uh but for many other cases uh it may not be you know there would be there would not be some kind of the some closed form uh for the k divergence but the thing is that for the simple the gausian distribution we can actually derive this kind of closed form the formulation for the k divergence so we're going to use this formulation uh for the many parts of like computer training the okay so actually that's kind of thing uh when it

0:48 comes to like using the gaus and the distribution uh many things became kind of the becomes like comfortable in terms of like we can derive those kind of closed form then we can compute all those kind of things but if we start to work on some like more the complexity distribution then there's no way to compute uh those things in a kind of like analytically way so that brings lots of the challenges and that's kind of the one of the many reasons like why we play with the gausian distribution so we talked about that we're going to use the uh standard gausian as the priority distribution And then also we're going to define the approximate the posterior also as the gausian distribution as well. Right? And based on that we're going to use those kind of use this kind of the formulation uh to measure the some the the quantity

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.