Learning to Identify Electrons

Abstract

We investigate whether state-of-the-art classification features commonly used to distinguish electrons from jet backgrounds in collider experiments are overlooking valuable information. A deep convolutional neural network analysis of electromagnetic and hadronic calorimeter deposits is compared to the performance of typical features, revealing a $\approx 5\%$ gap which indicates that these lower-level data do contain untapped classification power. To reveal the nature of this unused information, we use a recently developed technique to map the deep network into a space of physically interpretable observables. We identify two simple calorimeter observables which are not typically used for electron identification, but which mimic the decisions of the convolutional network and nearly close the performance gap.

10 pages, lots of figures, v2 for submission

References in corpus (27)

• PYTHIA 6.4 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Performance of electron reconstruction and selection with the CMS detector in proton-proton collisions at sqrt(s) = 8 TeV
• Energy Correlation Functions for Jet Substructure
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• A Convolutional Neural Network Neutrino Event Classifier
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Systematics of quark/gluon tagging
• Measurement of $W^{\pm }$ and $Z$-boson production cross sections in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Energy flow polynomials: A complete linear basis for jet substructure
• Electroweak Sector Under Scrutiny: A Combined Analysis of LHC and Electroweak Precision Data
• Search for supersymmetry in final states with jets, missing transverse momentum and one isolated lepton in sqrt{s} = 7 TeV pp collisions using 1 fb-1 of ATLAS data
• Weakly Supervised Classification in High Energy Physics
• Search for supersymmetry in pp collisions at sqrt(s) = 8 TeV in events with a single lepton, large jet multiplicity, and multiple b jets
• Particle-level pileup subtraction for jets and jet shapes
• Search for a Higgs boson in the decay channel H to ZZ(*) to q qbar l-l+ in pp collisions at sqrt(s) = 7 TeV
• (Machine) Learning to Do More with Less
• Mapping Machine-Learned Physics into a Human-Readable Space
• Searching for dilepton resonances below the Z mass at the LHC
• Electromagnetic Showers Beyond Shower Shapes
• Machine learning techniques in searches for $t\bar{t}h$ in the $h\to b\bar{b}$ decay channel

Cited by in corpus (12)

• Machine Learning in Nuclear Physics
• Resolving Extreme Jet Substructure
• Learning to Identify Semi-Visible Jets
• Learning to Isolate Muons
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• Particle identification with machine learning from incomplete data in the ALICE experiment
• NCoder -- A Quantum Field Theory approach to encoding data
• Machine-learning-based particle identification with missing data
• Jet Rotational Metrics
• Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
• Power Counting Energy Flow Polynomials
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure