Diederik P. Kingma

Adam: A Method for Stochastic Optimization

Auto-Encoding Variational Bayes

Semi-supervised Learning with Deep Generative Models

Weight normalization: a simple reparameterization to accelerate training of deep neural networks

Markov Chain Monte Carlo and Variational Inference: Bridging the Gap

Variational dropout and the local reparameterization trick

Variational Lossy Autoencoder

Improving Variational Inference with Inverse Autoregressive Flow.

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

Stochastic Gradient VB and the Variational Auto-Encoder