Particle Convolution for High Energy Physics

Abstract

We introduce the Particle Convolution Network (PCN), a new type of equivariant neural network layer suitable for many tasks in jet physics. The particle convolution layer can be viewed as an extension of Deep Sets and Energy Flow network architectures, in which the permutation-invariant operator is promoted to a group convolution. While the PCN can be implemented for various kinds of symmetries, we consider the specific case of rotation about the jet axis the $\eta -\varphi$ plane. In two standard benchmark tasks, q/g tagging and top tagging, we show that the rotational PCN (rPCN) achieves performance comparable to graph networks such as ParticleNet. Moreover, we show that it is possible to implement an IRC-safe rPCN, which significantly outperforms existing IRC-safe tagging methods on both tasks. We speculate that by generalizing the PCN to include additional convolutional symmetries relevant to jet physics, it may outperform the current state-of-the-art set by graph networks, while offering a new degree of control over physically-motivated inductive biases.

arXiv commentTo be presented at ML4Jets 2021

References in corpus (14)

• An Introduction to PYTHIA 8.2
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Identifying Boosted Objects with N-subjettiness
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Boosted objects: a probe of beyond the Standard Model physics
• Fat Jets for a Light Higgs
• Jet Substructure at the Large Hadron Collider: Experimental Review
• Quark and Gluon Tagging at the LHC
• Infrared safe definition of jet flavour
• Neural Networks for Impact Parameter Determination
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Boosting low-mass hadronic resonances

Cited by in corpus (6)

• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Symmetries, Safety, and Self-Supervision
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA