Safe but Incalculable: Energy-weighting is not all you need

TL;DR

This paper investigates the limitations of energy-weighting in IRC-safe neural networks for jet analysis, demonstrating how to improve robustness against non-perturbative effects with Lipschitz Energy Flow Networks.

Contribution

It introduces Lipschitz Energy Flow Networks (L-EFNs) that are IRC safe and less sensitive to non-perturbative corrections, advancing jet substructure analysis.

Findings

L-EFNs are more robust to hadronization effects.

EFNs are highly sensitive to non-perturbative effects.

Distinct latent representations are learned by EFNs and L-EFNs.

Abstract

Infrared and collinear (IRC) safety has long been used a proxy for robustness when developing new jet substructure observables. This guiding philosophy has been carried into the deep learning era, where IRC-safe neural networks have been used for many jet studies. For graph-based neural networks, the most straightforward way to achieve IRC safety is to weight particle inputs by their energies. However, energy-weighting by itself does not guarantee that perturbative calculations of machine-learned observables will enjoy small non-perturbative corrections. In this paper, we demonstrate the sensitivity of IRC-safe networks to non-perturbative effects, by training an energy flow network (EFN) to maximize its sensitivity to hadronization. We then show how to construct Lipschitz Energy Flow Networks (L-EFNs), which are both IRC safe and relatively insensitive to non-perturbative corrections. We demonstrate the performance of L-EFNs on generated samples of quark and gluon jets, and showcase fascinating differences between the learned latent representations of EFNs and L-EFNs.