Event Generation and Density Estimation with Surjective Normalizing Flows

TL;DR

This paper enhances normalizing flows with surjective and stochastic layers to better model complex features of particle collision events, improving their application in physics simulations and anomaly detection.

Contribution

It introduces novel surjective and stochastic transform layers into normalizing flows to handle permutation symmetry, varying dimensions, and discrete features in particle physics data.

Findings

Improved modeling of permutation symmetry and discrete features.

Enhanced generation quality for matrix element-level processes.

Better anomaly detection in LHC detector data.

Abstract

Normalizing flows are a class of generative models that enable exact likelihood evaluation. While these models have already found various applications in particle physics, normalizing flows are not flexible enough to model many of the peripheral features of collision events. Using the framework of Nielsen et al. (2020), we introduce several surjective and stochastic transform layers to a baseline normalizing flow to improve modelling of permutation symmetry, varying dimensionality and discrete features, which are all commonly encountered in particle physics events. We assess their efficacy in the context of the generation of a matrix element-level process, and in the context of anomaly detection in detector-level LHC events.