Learns an encoder to a latent distribution and a decoder back, trained on a lower bound of the likelihood. Gives a latent space you can interpolate in, at the cost of blurry samples.
supersedescorrects · extends
classifiesspecializes · part-of
substitutes forapproximates · alternative-to
depends onrequires · validates
Colour is the family; a dashed line is the second member of it.
Drag to pan · scroll to zoom · click a node to open it
This node
requiresdoes not work without Monte Carlo Integrationthe bound is estimated by sampling the latent
specializesis a specific case of Autoencoderadds a probabilistic latent and a likelihood bound
Referenced by
alternative-toGenerative Adversarial Network is a competing approach to thisan adversarial critic instead of a likelihood bound
requiresLatent Diffusion does not work without thisthe latent space it works in comes from one
requiresWorld Model does not work without thisthe latent its dynamics run in comes from one
References
Auto-Encoding Variational Bayes — Kingma, Welling — 2013 · link