Copula-Based Normalizing FlowsDownload PDF

Jun 02, 2021 (edited Jul 15, 2021)INNF+ 2021 posterReaders: Everyone
  • Keywords: Base Distribution, Copula, Expressiveness
  • TL;DR: We propose to generalize the Gaussian base distribution in a normalizing flow to a more elaborate copula distribution.
  • Abstract: Normalizing flows, which learn a distribution by transforming the data to samples from a Gaussian base distribution, have proven powerful density approximations. But their expressive power is limited by this choice of the base distribution. We, therefore, propose to generalize the base distribution to a more elaborate copula distribution to capture the properties of the target distribution more accurately. In a first empirical analysis, we demonstrate that this replacement can dramatically improve the vanilla normalizing flows in terms of flexibility, stability, and effectivity for heavy-tailed data. Our results suggest that the improvements are related to an increased local Lipschitz-stability of the learned flow.
3 Replies