Copula-Based Normalizing Flows
arXiv:2107.07352
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.
arXiv commentAccepted for presentation at the ICML 2021 Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+ 2021)
References in corpus (8)
- Auto-Encoding Variational Bayes
- Normalizing Flows: An Introduction and Review of Current Methods
- Density estimation using Real NVP
- Residual Flows for Invertible Generative Modeling
- The Devil is in the Tails: Fine-grained Classification in the Wild
- Tails of Lipschitz Triangular Flows
- Copula & Marginal Flows: Disentangling the Marginal from its Joint
- Robust model training and generalisation with Studentising flows