Improving Variational Inference with Inverse Autoregressive Flow

06/15/2016 ∙ by Diederik P. Kingma, et al. ∙ 0

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed flow consists of a chain of invertible transformations, where each transformation is based on an autoregressive neural network. In experiments, we show that IAF significantly improves upon diagonal Gaussian approximate posteriors. In addition, we demonstrate that a novel type of variational autoencoder, coupled with IAF, is competitive with neural autoregressive models in terms of attained log-likelihood on natural images, while allowing significantly faster synthesis.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

Code Repositories

keras-iaf-mnist

Implementation of Inverse Autoregressive Flows with Keras


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.