A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
arXiv:2203.05687 · doi:10.1103/PhysRevD.107.114029
Abstract
Precise reconstruction of top quark properties is a challenging task at the Large Hadron Collider due to combinatorial backgrounds and missing information. We introduce a physics-informed neural network architecture called the Covariant Particle Transformer (CPT) for directly predicting the top quark kinematic properties from reconstructed final state objects. This approach is permutation invariant and partially Lorentz covariant and can account for a variable number of input objects. In contrast to previous machine learning-based reconstruction methods, CPT is able to predict top quark four-momenta regardless of the jet multiplicity in the event. Using simulations, we show that the CPT performs favorably compared with other machine learning top quark reconstruction approaches.
arXiv comment10 pages, 4 figures. v2: fixed incorrect reference
References in corpus (36)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- The anti-k_t jet clustering algorithm
- An Introduction to PYTHIA 8.2
- FastJet user manual
- Dispelling the N^3 myth for the Kt jet-finder
- Automatic spin-entangled decays of heavy resonances in Monte Carlo simulations
- Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
- ParticleNet: Jet Tagging via Particle Clouds
- ATLAS -jet identification performance and efficiency measurement with events in collisions at TeV
- A framework for Higgs characterisation
- Energy Flow Networks: Deep Sets for Particle Jets
- Graph Neural Networks in Particle Physics
- Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
- JEDI-net: a jet identification algorithm based on interaction networks
- An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
- A likelihood-based reconstruction algorithm for top-quark pairs and the KLFitter framework
- Search for the Standard Model Higgs boson produced in association with top quarks and decaying into a pair in collisions at = 13 TeV with the ATLAS detector
- Properties of Higgs Boson Interactions with Top Quarks in the and Processes Using with the ATLAS Detector
- ABCNet: An attention-based method for particle tagging
- DisCo Fever: Robust Networks Through Distance Correlation
- Machine Learning Uncertainties with Adversarial Neural Networks
- A deep neural network to search for new long-lived particles decaying to jets
- Point Cloud Transformers applied to Collider Physics
- SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention
- uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
- Equivariant Energy Flow Networks for Jet Tagging
- Measurement of the production cross section in the all-jet final state in pp collisions at 13 TeV
- Learning to Simulate High Energy Particle Collisions from Unlabeled Data
- Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
- Mass Agnostic Jet Taggers
- QBDT, a new boosting decision tree method with systematic uncertainties into training for High Energy Physics
- Reducing the dependence of the neural network function to systematic uncertainties in the input space
- From the Bottom to the Top -- Reconstruction of Events with Deep Learning
- Enhancing searches for resonances with machine learning and moment decomposition
- Meta-learning and data augmentation for mass-generalised jet taggers
- New approaches for boosting to uniformity