Work

Ordering Dimensions with Nested Dropout Normalizing Flows

Year: 2020
Type: preprint
Abstract: The latent space of normalizing flows must be of the same dimensionality as their output space. This constraint presents a problem if we want to learn low-dimensional, semantically meaningful representations. Recent work has provided compact representations by fitting flows constrained to manifolds, but hasn't defined a density off that manifold. In this work we consider flows with full support in data space, but with ordered latent variables. Like in PCA, the leading latent dimensions define a sequence of manifolds that lie close to the data. We note a trade-off between the flow likelihood and the quality of the ordering, depending on the parameterization of the flow.
Language: English
Open Access status: green
OpenAlex ID: W3034465642
Cites: 19
Cited by: 9
Related to: 10