Interaction networks for the identification of boosted $H\to b\overline{b}$ decays

Abstract

We develop an algorithm based on an interaction network to identify high-transverse-momentum Higgs bosons decaying to bottom quark-antiquark pairs and distinguish them from ordinary jets that reflect the configurations of quarks and gluons at short distances. The algorithm's inputs are features of the reconstructed charged particles in a jet and the secondary vertices associated with them. Describing the jet shower as a combination of particle-to-particle and particle-to-vertex interactions, the model is trained to learn a jet representation on which the classification problem is optimized. The algorithm is trained on simulated samples of realistic LHC collisions, released by the CMS Collaboration on the CERN Open Data Portal. The interaction network achieves a drastic improvement in the identification performance with respect to state-of-the-art algorithms.

arXiv comment20 pages, 8 figures, 6 tables, version published in PRD

References in corpus (87)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• A Large Mass Hierarchy from a Small Extra Dimension
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Learning using Rectified Linear Units (ReLU)
• Parton distributions with LHC data
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Jet substructure as a new Higgs search channel at the LHC
• Particle-flow reconstruction and global event description with the CMS detector
• Soft Drop
• Event generator tunes obtained from underlying event and multiparton scattering measurements
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Towards an understanding of jet substructure
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• ParticleNet: Jet Tagging via Particle Clouds
• Energy Correlation Functions for Jet Substructure
• Deep Learning and its Application to LHC Physics
• Jet substructure as a new Higgs search channel at the LHC
• Pileup Per Particle Identification
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• 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
• 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
• WW scattering at the LHC
• Anomaly Detection for Resonant New Physics with Machine Learning
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• Domain-Adversarial Neural Networks
• The Machine Learning Landscape of Top Taggers
• Higgs boson pair production at NNLO with top quark mass effects
• Extending the Bump Hunt with Machine Learning
• Deep-learned Top Tagging with a Lorentz Layer
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• New Angles on Energy Correlation Functions
• QCD or What?
• Very boosted Higgs in gluon fusion
• Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
• Simulation Assisted Likelihood-free Anomaly Detection
• Energy flow polynomials: A complete linear basis for jet substructure
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• JEDI-net: a jet identification algorithm based on interaction networks
• The Metric Space of Collider Events
• QCD-Aware Recursive Neural Networks for Jet Physics
• Uncovering latent jet substructure
• Learning to Classify from Impure Samples with High-Dimensional Data
• Constraining Light-Quark Yukawa Couplings from Higgs Distributions
• Inclusive search for a highly boosted Higgs boson decaying to a bottom quark-antiquark pair
• Boosting $H\to b\bar{b}$ with Machine Learning
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• Weakly Supervised Classification in High Energy Physics
• Exposing the QCD Splitting Function with CMS Open Data
• Learning to Pivot with Adversarial Networks
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• Recursive Neural Networks in Quark/Gluon Tagging
• Novel Jet Observables from Machine Learning
• Measurement and interpretation of differential cross sections for Higgs boson production at $\sqrt{s}=$ 13 TeV
• Boosted Higgs Shapes
• Probing stop pair production at the LHC with graph neural networks
• Exploring the Space of Jets with CMS Open Data
• Modeling BSM effects on the Higgs transverse-momentum spectrum in an EFT approach
• (Machine) Learning to Do More with Less
• Jet Substructure Studies with CMS Open Data
• Mad-Maximized Higgs Pair Analyses
• Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks
• Usefulness of effective field theory for boosted Higgs production
• End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
• A multi-dimensional search for new heavy resonances decaying to boosted WW, WZ, or ZZ boson pairs in the dijet final state at 13 TeV
• Identification of boosted Higgs bosons decaying into $b$-quark pairs with the ATLAS detector at 13 TeV
• Mass Agnostic Jet Taggers
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Precise predictions for boosted Higgs production
• Graph Neural Networks for IceCube Signal Classification
• Effective Field Theory for Higgs properties parametrisation: the transverse momentum spectrum case
• A Dynamic Reduction Network for Point Clouds
• Exclusion of heavy, broad resonances from precise measurements of WZ and VH final states at the LHC

Cited by in corpus (42)

• Graph Neural Networks in Particle Physics
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• DisCo Fever: Robust Networks Through Distance Correlation
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• ABCDisCo: Automating the ABCD Method with Machine Learning
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Unveiling Hidden Physics at the LHC
• Casting a graph net to catch dark showers
• Charged particle tracking via edge-classifying interaction networks
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Graph Neural Networks for Charged Particle Tracking on FPGAs
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Jet Flavour Tagging for Future Colliders with Fast Simulation
• Higgs boson tagging with the Lund jet plane
• Search for nonresonant pair production of highly energetic Higgs bosons decaying to bottom quarks
• Probing triple Higgs coupling with machine learning at the LHC
• HHH Whitepaper
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA
• Secondary Vertex Finding in Jets with Neural Networks
• Machine Learning for Particle Flow Reconstruction at CMS
• Disentangling Boosted Higgs Boson Production Modes with Machine Learning
• Leveraging universality of jet taggers through transfer learning
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• GPU coprocessors as a service for deep learning inference in high energy physics
• Maximum performance of strange-jet tagging at hadron colliders
• Search for long-lived particles using displaced vertices and missing transverse momentum in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• FAIR AI Models in High Energy Physics
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• Portable acceleration of CMS computing workflows with coprocessors as a service
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
• Strange Jet Tagging
• Fast multilabel classification of HEP constraints with deep learning
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Top-philic Machine Learning
• Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
• HL-LHC sensitivity to higgsinos from natural SUSY with gravitino LSP
• Tagging the Higgs boson decay to bottom quarks with colour-sensitive observables and the Lund jet plane
• A FAIR and AI-ready Higgs boson decay dataset
• Explaining machine-learned particle-flow reconstruction