Does Lorentz-symmetric design boost network performance in jet physics?

TL;DR

This paper systematically investigates the impact of Lorentz-symmetric design in neural networks for jet physics, demonstrating that such symmetry acts as a beneficial inductive bias and improves network performance.

Contribution

It introduces two generalized methods for incorporating Lorentz symmetry into neural networks and confirms the performance benefits across multiple architectures.

Findings

Lorentz-symmetric design yields consistent performance gains.

The 'pairwise mass' feature's effectiveness is due to Lorentz symmetry compliance.

Preserving Lorentz symmetry acts as a strong inductive bias in jet physics networks.

Abstract

In the deep learning era, improving the neural network performance in jet physics is a rewarding task as it directly contributes to more accurate physics measurements at the LHC. Recent research has proposed various network designs in consideration of the full Lorentz symmetry, but its benefit is still not systematically asserted, given that there remain many successful networks without taking it into account. We conduct a detailed study on the Lorentz-symmetric design. We propose two generalized approaches for modifying a network - these methods are experimented on Particle Flow Network, ParticleNet, and LorentzNet, and exhibit a general performance gain. We also reveal that the notable improvement attributed to the "pairwise mass" feature in the network is due to its introduction of a structure that fully complies with Lorentz symmetry. We confirm that Lorentz-symmetry preservation serves as a strong inductive bias of jet physics, hence calling for attention to such general recipes in future network designs.