Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
arXiv:2003.11787 · doi:10.1007/JHEP07(2020)111
Abstract
Deep neural networks trained on jet images have been successful in classifying different kinds of jets. In this paper, we identify the crucial physics features that could reproduce the classification performance of the convolutional neural network in the top jet vs. QCD jet classification. We design a neural network that considers two types of substructural features: two-point energy correlations, and the IRC unsafe counting variables of a morphological analysis of jet images. The new set of IRC unsafe variables can be described by Minkowski functionals from integral geometry. To integrate these features into a single framework, we reintroduce two-point energy correlations in terms of a graph neural network and provide the other features to the network afterward. The network shows a comparable classification performance to the convolutional neural network. Since both networks are using IRC unsafe features at some level, the results based on simulations are often dependent on the event generator choice. We compare the classification results of Pythia 8 and Herwig 7, and a simple reweighting on the distribution of IRC unsafe features reduces the difference between the results from the two simulations.
arXiv comment43 pages, 25 figures, published in JHEP
References in corpus (106)
- 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
- DELPHES 3, A modular framework for fast simulation of a generic collider experiment
- Parton distributions for the LHC Run II
- Herwig++ Physics and Manual
- Parton distributions with LHC data
- Parton distributions from high-precision collider data
- Herwig 7.0 / Herwig++ 3.0 Release Note
- Successive Combination Jet Algorithm For Hadron Collisions
- Jet substructure as a new Higgs search channel at the LHC
- Tuning PYTHIA 8.1: the Monash 2013 Tune
- Identifying Boosted Objects with N-subjettiness
- Soft Drop
- Jet Trimming
- Parton distributions with QED corrections
- Towards an understanding of jet substructure
- Top-tagging: A Method for Identifying Boosted Hadronic Tops
- A first unbiased global NLO determination of parton distributions and their uncertainties
- Energy Correlation Functions for Jet Substructure
- Deep Learning and its Application to LHC Physics
- Transverse-Momentum-Ordered Showers and Interleaved Multiple Interactions
- Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
- Impact of Heavy Quark Masses on Parton Distributions and LHC Phenomenology
- Fat Jets for a Light Higgs
- Anomaly Detection with Density Estimation
- Jet Substructure at the Large Hadron Collider: Experimental Review
- Classification without labels: Learning from mixed samples in high energy physics
- Stop Reconstruction with Tagged Tops
- Deep learning in color: towards automated quark/gluon jet discrimination
- Jet-Images -- Deep Learning Edition
- Deep-learning Top Taggers or The End of QCD?
- Searching for New Physics with Deep Autoencoders
- Strategies to Identify Boosted Tops
- Energy Flow Networks: Deep Sets for Particle Jets
- Colour reconnections in Herwig++
- Minkowski Functionals used in the Morphological Analysis of Cosmic Microwave Background Anisotropy Maps
- New formalism for QCD parton showers
- Power Counting to Better Jet Observables
- Gaining (Mutual) Information about Quark/Gluon Discrimination
- Beyond genus statistics: a unifying approach to the morphology of cosmic structure
- Neural Network Parametrization of Deep-Inelastic Structure Functions
- Deep-learned Top Tagging with a Lorentz Layer
- Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
- Seeing in Color: Jet Superstructure
- A determination of the fragmentation functions of pions, kaons, and protons with faithful uncertainties
- New Angles on Energy Correlation Functions
- Systematics of quark/gluon tagging
- How to GAN LHC Events
- OmniFold: A Method to Simultaneously Unfold All Observables
- QCD or What?
- Quark and Gluon Jet Substructure
- Novelty Detection Meets Collider Physics
- Adversarially-trained autoencoders for robust unsupervised new physics searches
- Energy flow polynomials: A complete linear basis for jet substructure
- Learning representations of irregular particle-detector geometry with distance-weighted graph networks
- Finding top quarks with shower deconstruction
- Primordial Non-Gaussianity and Analytical Formula for Minkowski Functionals of the Cosmic Microwave Background and Large-scale Structure
- Finding physics signals with shower deconstruction
- Precision determination of electroweak parameters and the strange content of the proton from neutrino deep-inelastic scattering
- Pulling Out All the Tops with Computer Vision and Deep Learning
- JEDI-net: a jet identification algorithm based on interaction networks
- QCD-Aware Recursive Neural Networks for Jet Physics
- Pileup Mitigation with Machine Learning (PUMML)
- JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
- Uncovering latent jet substructure
- Neural network determination of parton distributions: the nonsinglet case
- Multivariate discrimination and the Higgs + W/Z search
- Exploring phase space with Neural Importance Sampling
- ABCNet: An attention-based method for particle tagging
- Casimir Meets Poisson: Improved Quark/Gluon Discrimination with Counting Observables
- Boosting with Machine Learning
- DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
- Weakly Supervised Classification in High Energy Physics
- Jet Substructure Without Trees
- How to GAN away Detector Effects
- Recursive Neural Networks in Quark/Gluon Tagging
- Minkowski Functional Description of Microwave Background Gaussianity
- Measuring Multijet Structure of Hadronic Energy Flow Or What IS A Jet?
- Topology and Geometry of Gaussian random fields I: on Betti Numbers, Euler characteristic and Minkowski functionals
- Finding physics signals with event deconstruction
- Probing stop pair production at the LHC with graph neural networks
- Neural network parametrization of spectral functions from hadronic tau decays and determination of QCD vacuum condensates
- Recursive Soft Drop
- Jet Dipolarity: Top Tagging with Color Flow
- Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC
- Deep-Learning Jets with Uncertainties and More
- Unbiased determination of the proton structure function F_2^p with faithful uncertainty estimation
- Supervised deep learning in high energy phenomenology: a mini review
- Lund jet images from generative and cycle-consistent adversarial networks
- Non-Gaussian morphology on large scales: Minkowski functionals of the REFLEX cluster catalogue
- Using neural networks for efficient evaluation of high multiplicity scattering amplitudes
- Morphometry of Spatial Patterns
- Infrared Safety of a Neural-Net Top Tagging Algorithm
- Binary JUNIPR: an interpretable probabilistic model for discrimination
- Persistent Homology and Non-Gaussianity
- Precision determination of alpha_s using an unbiased global NLO parton set
- Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
- On Minkowski Functionals of CMB polarization
- Determination of alpha_s from scaling violations of truncated moments of structure functions
- CapsNets Continuing the Convolutional Quest
- Angular Scaling in Jets
- Morphometric analysis in gamma-ray astronomy using Minkowski functionals - Source detection via structure quantification
- QCD Analysis of the Scale-Invariance of Jets
- Deep Learning Jet Substructure from Two-Particle Correlation
Cited by in corpus (22)
- An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
- ABCDisCo: Automating the ABCD Method with Machine Learning
- Casting a graph net to catch dark showers
- Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
- The Boosted Higgs Jet Reconstruction via Graph Neural Network
- Higgs boson tagging with the Lund jet plane
- Probing triple Higgs coupling with machine learning at the LHC
- Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
- Exploring Jet Substructure in Semi-visible jets
- Jet Discrimination with Quantum Complete Graph Neural Network
- Maximum performance of strange-jet tagging at hadron colliders
- Comparing Point Cloud Strategies for Collider Event Classification
- Boosted top tagging and its interpretation using Shapley values
- Jet Classification Using High-Level Features from Anatomy of Top Jets
- Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
- Fat -Jet Analyses Using Old and New Clustering Algorithms in New Higgs Boson Searches at the LHC
- Probing sub-TeV Higgsinos aided by a ML-based top tagger in the context of Trilinear RPV SUSY
- Top-philic Machine Learning
- DeeLeMa: Missing information search with Deep Learning for Mass estimation
- Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
- Tagging ultra-boosted jets at FCC-hh using machine learning techniques
- Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features