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.
|Number of pages||6|
|Publication status||Published - 18 Jul 2020|
|Event||ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models 2020 - Virtual workshop|
Duration: 13 Jul 2020 → 13 Jul 2020
|Workshop||ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models 2020|
|Abbreviated title||INNF+ 2020|
|Period||13/07/20 → 13/07/20|