Auto-Encoding Variational Bayes

Diederik P. Kingma, Max Welling

Dec 23, 2013 (modified: Dec 23, 2013) ICLR 2014 conference submission readers: everyone
  • Decision: submitted, no decision
  • Abstract: Can we efficiently learn the parameters of directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions? We introduce an unsupervised on-line learning method that efficiently optimizes the variational lower bound on the marginal likelihood and that, under some mild conditions, even works in the intractable case. The method optimizes a probabilistic encoder (also called a recognition network) to approximate the intractable posterior distribution of the latent variables. The crucial element is a reparameterization of the variational bound with an independent noise variable, yielding a stochastic objective function which can be jointly optimized w.r.t. variational and generative parameters using standard gradient-based stochastic optimization methods. Theoretical advantages are reflected in experimental results.