Equivariant Energy Flow Networks for Jet Tagging

TL;DR

This paper introduces permutation-equivariant Energy Flow Networks for jet tagging, maintaining safety properties and achieving performance comparable to Particle Flow Networks, while addressing convergence and overfitting issues.

Contribution

It develops a novel equivariant EFN architecture based on Deep Sets, analyzing safety conditions and demonstrating its effectiveness in jet tagging tasks.

Findings

Equivariant EFNs perform similarly to Particle Flow Networks.

Standard EFNs outperform equivariant variants in some cases.

Equivariant networks help in jet mass decorrelation.

Abstract

Jet tagging techniques that make use of deep learning show great potential for improving physics analyses at colliders. One such method is the Energy Flow Network (EFN) - a recently introduced neural network architecture that represents jets as permutation-invariant sets of particle momenta while maintaining infrared and collinear safety. We develop a variant of the Energy Flow Network architecture based on the Deep Sets formalism, incorporating permutation-equivariant layers. We derive conditions under which infrared and collinear safety can be maintained, and study the performance of these networks on the canonical example of W-boson tagging. We find that equivariant Energy Flow Networks have similar performance to Particle Flow Networks, which are superior to standard EFNs. However, equivariant Particle Flow Networks suffer from convergence and overfitting issues. Finally, we study how equivariant networks sculpt the jet mass and provide some initial results on decorrelation using planing.