Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks

Abstract

Top quarks, produced in large numbers at the Large Hadron Collider, have a complex detector signature and require special reconstruction techniques. The most common decay mode, the "all-jet" channel, results in a 6-jet final state which is particularly difficult to reconstruct in $pp$ collisions due to the large number of permutations possible. We present a novel approach to this class of problem, based on neural networks using a generalized attention mechanism, that we call Symmetry Preserving Attention Networks (SPA-Net). We train one such network to identify the decay products of each top quark unambiguously and without combinatorial explosion as an example of the power of this technique.This approach significantly outperforms existing state-of-the-art methods, correctly assigning all jets in $93.0$ of $6$-jet, $87.8$ of $7$-jet, and $82.6$ of $\ge 8$-jet events respectively.

replaced with final published version

References in corpus (7)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• An Introduction to PYTHIA 8.2
• Boosted objects: a probe of beyond the Standard Model physics
• Gauge Equivariant Convolutional Networks and the Icosahedral CNN
• Lorentz Group Equivariant Neural Network for Particle Physics
• Search for vector-like T quarks decaying to top quarks and Higgs bosons in the all-hadronic channel using jet substructure
• Measurement of differential $\mathrm{t}\bar{\mathrm{t}}$ production cross sections using top quarks at large transverse momenta in pp collisions at $\sqrt{s}=$ 13 TeV

Cited by in corpus (21)

• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• ν-Flows: Conditional Neutrino Regression
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• ${\nu }^2$-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows
• Resolving Extreme Jet Substructure
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Portraying Double Higgs at the Large Hadron Collider II
• Does Lorentz-symmetric design boost network performance in jet physics?
• Parameter Inference from Event Ensembles and the Top-Quark Mass
• Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks
• Reconstructing short-lived particles using hypergraph representation learning
• Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks
• Top-philic Machine Learning
• Determination of the initial condition for the Balitsky-Kovchegov equation with transformers
• PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
• Quantum-annealing-inspired algorithms for multijet clustering
• Solving Combinatorial Problems at Particle Colliders Using Machine Learning
• TIGER: A Topology-Agnostic, Hierarchical Graph Network for Event Reconstruction
• Transformer Neural Networks in the Measurement of $t\bar{t}H$ Production in the $H\to b\bar{b}$ Decay Channel with ATLAS