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.
Bibtex
@misc{jaini2019tails,
title={Tails of Lipschitz Triangular Flows},
author={Priyank Jaini and Ivan Kobyzev and Yaoliang Yu and Marcus Brubaker},
year={2019},
eprint={1907.04481},
archivePrefix={arXiv},
primaryClass={math.ST}
}
Related Research
-
Our NeurIPS 2021 Reading List
Our NeurIPS 2021 Reading List
Y. Cao, K. Y. C. Lui, T. Durand, J. He, P. Xu, N. Mehrasa, A. Radovic, A. Lehrmann, R. Deng, A. Abdi, M. Schlegel, and S. Liu.
Computer Vision; Data Visualization; Graph Representation Learning; Learning And Generalization; Natural Language Processing; Optimization; Reinforcement Learning; Time series Modelling; Unsupervised Learning
Research
-
On Variational Learning of Controllable Representations for Text without Supervision
On Variational Learning of Controllable Representations for Text without Supervision
P. Xu, J. Chi Kit Cheung, and Y. Cao. International Conference on Machine Learning (ICML)
Publications
-
Unsupervised Multilingual Alignment using Wasserstein Barycenter
Unsupervised Multilingual Alignment using Wasserstein Barycenter
X. Lian, K. Jain, J. Truszkowski, P. Poupart, and Y. Yu. International Joint Conference on Artificial Intelligence (IJCAI)
Publications