Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Improving Variational Inference with Inverse Autoregressive Flow

About

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.

Diederik P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, Max Welling• 2016

Related benchmarks

TaskDatasetResultRank
Generative ModelingCIFAR-10
BPD3.11
46
Unconditional Image GenerationImageNet-32
BPD3.11
31
Showing 2 of 2 rows

Other info

Follow for update