Back to timeline

Research · December 2013

The variational autoencoder

Kingma and Welling showed how to train a generative model with latent variables by gradient descent, by making randomness differentiable.

Why it matters

Probabilistic modelling and deep networks met in one method trainable by ordinary back-propagation.

The key device is reparameterisation: a random variable is written as a deterministic function of parameters and independent noise, and the gradient passes straight through. That removed the obstacle keeping probabilistic models from using deep networks. The method gives both generation and a compressed representation. Diffusion models belong to the same family of explicitly probabilistic approaches.

Event record

Event date
December 2013
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0225

Preprint of 20 December 2013; presented at ICLR 2014.

Sources

Related events