Testing the boundaries: Normalizing Flows for higher dimensional data sets

TL;DR

This paper evaluates the robustness and performance of various Normalizing Flows on high-dimensional toy datasets, highlighting their potential and limitations for complex data in High Energy Physics.

Contribution

It systematically assesses how different types of Normalizing Flows perform as data dimensionality increases, providing insights into their scalability and robustness.

Findings

Normalizing Flows maintain performance up to certain dimensions

Performance degrades as data dimensionality increases

Some NF architectures are more robust than others in high dimensions

Abstract

Normalizing Flows (NFs) are emerging as a powerful class of generative models, as they not only allow for efficient sampling, but also deliver, by construction, density estimation. They are of great potential usage in High Energy Physics (HEP), where complex high dimensional data and probability distributions are everyday's meal. However, in order to fully leverage the potential of NFs it is crucial to explore their robustness as data dimensionality increases. Thus, in this contribution, we discuss the performances of some of the most popular types of NFs on the market, on some toy data sets with increasing number of dimensions.