Jet Rotational Metrics

Abstract

Embedding symmetries in the architectures of deep neural networks can improve classification and network convergence in the context of jet substructure. These results hint at the existence of symmetries in jet energy depositions, such as rotational symmetry, arising from the physical features of the underlying processes. We introduce new jet observables, Jet Rotational Metrics (JRMs), which provide insights into the substructure of jets by comparing them to jets with perfect discrete rotational symmetry. We show that JRMs are formidable jet features, achieving good classification scores when used as inputs to deep neural networks. We also show that when used in combination with other jet observables, like N-subjettiness and EFPs, our features increase classification performance. The results suggest that JRMs may capture information not efficiently captured by the other observables, motivating the design of future jet observables for learning the underlying symmetries in the physical processes.

References in corpus (11)

• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Systematics of quark/gluon tagging
• Energy flow polynomials: A complete linear basis for jet substructure
• The Metric Space of Collider Events
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention
• Computing $N$-subjettiness for boosted jets
• Learning to Identify Electrons
• Resolving Extreme Jet Substructure
• Learning to Identify Semi-Visible Jets

Cited by in corpus (1)

• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction