Sylvester Normalizing Flows for Variational Inference
Machine Learning
2019-02-21 v2 Artificial Intelligence
Machine Learning
Methodology
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.
Keywords
Cite
@article{arxiv.1803.05649,
title = {Sylvester Normalizing Flows for Variational Inference},
author = {Rianne van den Berg and Leonard Hasenclever and Jakub M. Tomczak and Max Welling},
journal= {arXiv preprint arXiv:1803.05649},
year = {2019}
}
Comments
Published at UAI 2018, 12 pages, 3 figures, code at: https://github.com/riannevdberg/sylvester-flows