BIP: Boost Invariant Polynomials for Efficient Jet Tagging

Abstract

Deep Learning approaches are becoming the go-to methods for data analysis in High Energy Physics (HEP). Nonetheless, most physics-inspired modern architectures are computationally inefficient and lack interpretability. This is especially the case with jet tagging algorithms, where computational efficiency is crucial considering the large amounts of data produced by modern particle detectors. In this work, we present a novel, versatile and transparent framework for jet representation; invariant to Lorentz group boosts, which achieves high accuracy on jet tagging benchmarks while being orders of magnitudes faster to train and evaluate than other modern approaches for both supervised and unsupervised schemes.

References in corpus (8)

• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
• Lorentz Group Equivariant Neural Network for Particle Physics
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Particle Transformer for Jet Tagging
• Multilayer atomic cluster expansion for semi-local interactions
• The Exploitation of Distance Distributions for Clustering
• Optimal Evaluation of Symmetry-Adapted $n$-Correlations Via Recursive Contraction of Sparse Symmetric Tensors

Cited by in corpus (4)

• Explainable Equivariant Neural Networks for Particle Physics: PELICAN
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Does Lorentz-symmetric design boost network performance in jet physics?
• Tagging ultra-boosted jets at FCC-hh using machine learning techniques