Practical Synthesis of Mixed-Tailed Data with Normalizing Flows
Abstract
Capturing the correct tail behavior is difficult, yet essential for a faithful generative model. In this work, we provide an improved framework for training flows-based models with robust capabilities to capture the tail behavior of mixed-tail data. We propose a combination of a tail-flexible base distribution and a robust training algorithm to enable the flow to model heterogeneous tail behavior in the target distribution. We support our claim with extensive experiments on synthetic and real world data.
Cite
Text
Amiri et al. "Practical Synthesis of Mixed-Tailed Data with Normalizing Flows." Transactions on Machine Learning Research, 2024.Markdown
[Amiri et al. "Practical Synthesis of Mixed-Tailed Data with Normalizing Flows." Transactions on Machine Learning Research, 2024.](https://mlanthology.org/tmlr/2024/amiri2024tmlr-practical/)BibTeX
@article{amiri2024tmlr-practical,
title = {{Practical Synthesis of Mixed-Tailed Data with Normalizing Flows}},
author = {Amiri, Saba and Nalisnick, Eric and Belloum, Adam and Klous, Sander and Gommans, Leon},
journal = {Transactions on Machine Learning Research},
year = {2024},
url = {https://mlanthology.org/tmlr/2024/amiri2024tmlr-practical/}
}