---
title: "Auto-Encoding Variational Bayes"
description: "Auto-Encoding Variational Bayes makes latent-variable models trainable with ordinary backpropagation. Read it to see how the evidence lower bound, amortized inference, and the reparameterization trick turn an intractable posterior problem into a practical stochastic-optimization recipe."
canonical_url: "https://fanout.sh/daily/2026-07-24-auto-encoding-variational-bayes"
md_url: "https://fanout.sh/daily/2026-07-24-auto-encoding-variational-bayes.md"
last_updated: "2026-07-24"
access: "public"
---

# Auto-Encoding Variational Bayes

Auto-Encoding Variational Bayes makes latent-variable models trainable with ordinary backpropagation. Read it to see how the evidence lower bound, amortized inference, and the reparameterization trick turn an intractable posterior problem into a practical stochastic-optimization recipe.

## Paper details

- Authors: Kingma and Welling

- Venue: ICLR 2014

- Track: ML Math

- Difficulty: Hard

- Reading time: 55 min

- Original paper: https://arxiv.org/abs/1312.6114

## What you will learn

- How the evidence lower bound replaces an intractable log-likelihood with reconstruction and KL terms that can be optimized.

- Why an encoder amortizes posterior inference by predicting a distribution over latent variables for each example.

- How reparameterizing a sample as a deterministic transform of parameter-free noise lets gradients pass through stochastic latent variables.

## Continue exploring

[Explore Variational Autoencoders](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Avariational-autoencoder-vae): Open Fanout's VAE concept node and connect the paper to latent-variable models, the ELBO, KL divergence, and generative modeling.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md