Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
arXiv:2004.08262 · doi:10.1088/1748-0221/15/06/P06005
Abstract
Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at 13 TeV, corresponding to an integrated luminosity of 35.9 fb. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.
Replaced with the published version. Added the journal reference and the DOI. All the figures and tables can be found at http://cms-results.web.cern.ch/cms-results/public-results/publications/JME-18-002 (CMS Public Pages)
References in corpus (26)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- ADADELTA: An Adaptive Learning Rate Method
- Herwig++ Physics and Manual
- Comparative study of various algorithms for the merging of parton showers and matrix elements in hadronic collisions
- Particle-flow reconstruction and global event description with the CMS detector
- Tuning PYTHIA 8.1: the Monash 2013 Tune
- The CMS trigger system
- Description and performance of track and primary-vertex reconstruction with the CMS tracker
- Performance of CMS muon reconstruction in pp collision events at sqrt(s) = 7 TeV
- Jet energy scale and resolution in the CMS experiment in pp collisions at 8 TeV
- Performance of electron reconstruction and selection with the CMS detector in proton-proton collisions at sqrt(s) = 8 TeV
- Pileup Per Particle Identification
- Performance of missing transverse momentum reconstruction in proton-proton collisions at 13 TeV using the CMS detector
- Jet mass and substructure of inclusive jets in sqrt(s) = 7 TeV pp collisions with the ATLAS experiment
- New Angles on Energy Correlation Functions
- Pileup mitigation at CMS in 13 TeV data
- Identification techniques for highly boosted W bosons that decay into hadrons
- Search for low mass vector resonances decaying into quark-antiquark pairs in proton-proton collisions at sqrt(s) = 13 TeV
- Search for direct production of supersymmetric partners of the top quark in the all-jets final state in proton-proton collisions at sqrt(s) = 13 TeV
- Herwig 7.2 Release Note
- Measurement of the B+- production cross-section in pp collisions at sqrt(s)=7 TeV
- Search for heavy resonances that decay into a vector boson and a Higgs boson in hadronic final states at sqrt(s) = 13 TeV
- Search for electroweak production of charginos and neutralinos in WH events in proton-proton collisions at sqrt(s) = 13 TeV
- Measurement of the cross-section of high transverse momentum vector bosons reconstructed as single jets and studies of jet substructure in collisions at = 7 TeV with the ATLAS detector
- Searches for W' bosons decaying to a top quark and a bottom quark in proton-proton collisions at 13 TeV
- Search for decays of neutral beauty mesons into four muons
Cited by in corpus (87)
- 50 Years of Quantum Chromodynamics
- Pileup mitigation at CMS in 13 TeV data
- An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
- Search for new particles in events with energetic jets and large missing transverse momentum in proton-proton collisions at 13 TeV
- Analyzing N-point Energy Correlators Inside Jets with CMS Open Data
- Search for supersymmetry in final states with two oppositely charged same-flavor leptons and missing transverse momentum in proton-proton collisions at 13 TeV
- MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
- Search for singly and pair-produced leptoquarks coupling to third-generation fermions in proton-proton collisions at 13 TeV
- ABCDisCo: Automating the ABCD Method with Machine Learning
- Search for top squark production in fully-hadronic final states in proton-proton collisions at 13 TeV
- Identification of hadronic tau lepton decays using a deep neural network
- Optimisation of large-radius jet reconstruction for the ATLAS detector in 13 TeV proton-proton collisions
- Mapping Machine-Learned Physics into a Human-Readable Space
- Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
- PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
- Review of searches for vector-like quarks, vector-like leptons, and heavy neutral leptons in proton-proton collisions at = 13 TeV at the CMS experiment
- A search for decays of the Higgs boson to invisible particles in events with a top-antitop quark pair or a vector boson in proton-proton collisions at = 13 TeV
- Combined searches for the production of supersymmetric top quark partners in proton-proton collisions at 13 TeV
- Unsupervised Outlier Detection in Heavy-Ion Collisions
- Search for electroweak production of charginos and neutralinos at = 13 TeV in final states containing hadronic decays of WW, WZ, or WH and missing transverse momentum
- Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
- A fast centrality-meter for heavy-ion collisions at the CBM experiment
- The Boosted Higgs Jet Reconstruction via Graph Neural Network
- Search for Higgs boson decay to a charm quark-antiquark pair in proton-proton collisions at = 13 TeV
- Jet Flavour Tagging for Future Colliders with Fast Simulation
- A Cautionary Tale of Decorrelating Theory Uncertainties
- Dark sector searches with the CMS experiment
- Search for nonresonant pair production of highly energetic Higgs bosons decaying to bottom quarks
- Search for single production of a vector-like T quark decaying to a top quark and a Z boson in the final state with jets and missing transverse momentum at 13 TeV
- Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
- Enriching the physics program of the CMS experiment via data scouting and data parking
- Non-Gaussianities in Collider Energy Flux
- HHH Whitepaper
- Measurement of the differential production cross section as a function of the jet mass and extraction of the top quark mass in hadronic decays of boosted top quarks
- Measurement of differential production cross sections using top quarks at large transverse momenta in pp collisions at 13 TeV
- Combined search for electroweak production of winos, binos, higgsinos, and sleptons in proton-proton collisions at = 13 TeV
- Search for chargino-neutralino production in events with Higgs and W bosons using 137 fb of proton-proton collisions at 13 TeV
- A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
- Searches for Higgs boson production through decays of heavy resonances
- Leveraging universality of jet taggers through transfer learning
- GPU coprocessors as a service for deep learning inference in high energy physics
- Search for W' bosons decaying to a top and a bottom quark at 13 TeV in the hadronic final state
- Search for new heavy resonances decaying to WW, WZ, ZZ, WH, or ZH boson pairs in the all-jets final state in proton-proton collisions at = 13 TeV
- Status of searches for electroweak-scale supersymmetry after LHC Run 2
- Boosted top quark tagging and polarization measurement using machine learning
- Stairway to discovery: a report on the CMS programme of cross section measurements from millibarns to femtobarns
- Searches for new physics with boosted top quarks in the MadAnalysis 5 and Rivet frameworks
- Does Lorentz-symmetric design boost network performance in jet physics?
- Maximum performance of strange-jet tagging at hadron colliders
- Bias and Priors in Machine Learning Calibrations for High Energy Physics
- Search for single production of vectorlike -quarks at the LHC
- Semi-supervised Graph Neural Networks for Pileup Noise Removal
- Search for a heavy resonance decaying to a top quark and a W boson at 13 TeV in the fully hadronic final state
- Search for heavy resonances decaying to a pair of Lorentz-boosted Higgs bosons in final states with leptons and a bottom quark pair at 13 TeV
- Using Machine Learning to Improve Neutron Identification in Water Cherenkov Detectors
- Accuracy versus precision in boosted top tagging with the ATLAS detector
- Search for new physics using effective field theory in 13 TeV pp collision events that contain a top quark pair and a boosted Z or Higgs boson
- Climbing to the Top of the ATLAS 13 TeV data
- Higgs and top physics reconstruction challenges and opportunities at FCC-ee
- A machine learning-based study of open-charm hadrons in proton-proton collisions at the Large Hadron Collider
- Portable acceleration of CMS computing workflows with coprocessors as a service
- Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
- Machine-Learning Performance on Higgs-Pair Production Associated with Dark Matter at the LHC
- Performance of heavy-flavour jet identification in Lorentz-boosted topologies in proton-proton collisions at = 13 TeV
- End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data
- Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments
- Dark Matter Searches with Top Quarks
- Measurement of the charge asymmetry in events with highly Lorentz-boosted top quarks in pp collisions at = 13 TeV
- Search for pair production of heavy particles decaying to a top quark and a gluon in the lepton+jets final state in proton-proton collisions at = 13 TeV
- Search for resonances decaying to three W bosons in the hadronic final state in proton-proton collisions at 13 TeV
- Measurement of jet substructure in boosted events with the ATLAS detector using 140 fb of 13 TeV collisions
- Neural networks for boosted di- identification
- Search for resonances decaying to three W bosons in proton-proton collisions at 13 TeV
- Tagging a Boosted Top quark with a final state
- Sequence-based Machine Learning Models in Jet Physics
- Searching for New Physics in Hadronic Final States with Run 2 Proton-Proton Collision Data at the LHC
- Measurement of the Lund jet plane in hadronic decays of top quarks and W bosons with the ATLAS detector
- Probing Light Scalars and Vector-like Quarks at the High-Luminosity LHC
- The SMARTHEP European Training Network
- Search for heavy resonances decaying to Z()V(qq') in proton-proton collisions at 13 TeV
- HL-LHC sensitivity to higgsinos from natural SUSY with gravitino LSP
- Image-Based Jet Analysis
- Tagging the Higgs boson decay to bottom quarks with colour-sensitive observables and the Lund jet plane
- Vision Transformers for End-to-End Quark-Gluon Jet Classification from Calorimeter Images
- The Physics Behind ML-based Quark-Gluon Taggers
- Machine learning driven identification of heavy flavor decay leptons in proton-proton collisions at the Large Hadron Collider
- Boosted and semi-boosted all-hadronic reconstruction performance on kinematic variables for selected BSM models using a 2D extesion of the BumpHunter algorithm