English

Tails of Lipschitz Triangular Flows

Statistics Theory 2020-09-22 v3 Machine Learning Machine Learning Statistics Theory

Abstract

We investigate the ability of popular flow based methods to capture tail-properties of a target density by studying the increasing triangular maps used in these flow methods acting on a tractable source density. We show that the density quantile functions of the source and target density provide a precise characterization of the slope of transformation required to capture tails in a target density. We further show that any Lipschitz-continuous transport map acting on a source density will result in a density with similar tail properties as the source, highlighting the trade-off between a complex source density and a sufficiently expressive transformation to capture desirable properties of a target density. Subsequently, we illustrate that flow models like Real-NVP, MAF, and Glow as implemented originally lack the ability to capture a distribution with non-Gaussian tails. We circumvent this problem by proposing tail-adaptive flows consisting of a source distribution that can be learned simultaneously with the triangular map to capture tail-properties of a target density. We perform several synthetic and real-world experiments to compliment our theoretical findings.

Cite

@article{arxiv.1907.04481,
  title  = {Tails of Lipschitz Triangular Flows},
  author = {Priyank Jaini and Ivan Kobyzev and Yaoliang Yu and Marcus Brubaker},
  journal= {arXiv preprint arXiv:1907.04481},
  year   = {2020}
}

Comments

Published at the 37th International Conference of Machine Learning, (ICML 2020)

R2 v1 2026-06-23T10:16:59.134Z