Sylvester Normalizing Flows for

Rianne van den Berg∗
University of Amsterdam
Leonard Hasenclever∗
University of Oxford
Jakub M. Tomczak
University of Amsterdam
Max Welling
University of Amsterdam

https://arxiv.org/pdf/1803.05649.pdf

Abstract

Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a generalization of planar flows. Sylvester normalizing flows remove the well-known single-unit bottleneck from planar flows, making a single transformation much more flexible. We compare the performance of Sylvester normalizing flows against planar flows and inverse autoregressive flows and demonstrate that they compare favorably on several datasets.