PaperSwipe

Copula-Based Normalizing Flows

Published 4 years agoVersion 1arXiv:2107.07352

Authors

Mike Laszkiewicz, Johannes Lederer, Asja Fischer

Categories

cs.LGcs.AIstat.ML

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.

Copula-Based Normalizing Flows

4 years ago
v1
3 authors

Categories

cs.LGcs.AIstat.ML

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.

Authors

Mike Laszkiewicz, Johannes Lederer, Asja Fischer

arXiv ID: 2107.07352
Published Jul 15, 2021

Click to preview the PDF directly in your browser