Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks

Abstract

Machine learning methods incorporating deep neural networks have been the subject of recent proposals for new hadronic resonance taggers. These methods require training on a dataset produced by an event generator where the true class labels are known. However, training a network on a specific event generator may bias the network towards learning features associated with the approximations to QCD used in that generator which are not present in real data. We therefore investigate the effects of variations in the modelling of the parton shower on the performance of deep neural network taggers using jet images from hadronic W-bosons at the LHC, including detector-related effects. By investigating network performance on samples from the Pythia, Herwig and Sherpa generators, we find differences of up to fifty percent in background rejection for fixed signal efficiency. We also introduce and study a method, which we dub zooming, for implementing scale-invariance in neural network-based taggers. We find that this leads to an improvement in performance across a wide range of jet transverse momenta. Our results emphasise the importance gaining a detailed understanding what aspects of jet physics these methods are exploiting.

9 pages, 4 figures; v2: plots updated, references added

References in corpus (12)

• The NumPy array: a structure for efficient numerical computation
• An Introduction to PYTHIA 8.2
• Event generation with SHERPA 1.1
• Herwig++ Physics and Manual
• A parton shower algorithm based on Catani-Seymour dipole factorisation
• Jet substructure as a new Higgs search channel at the LHC
• Jet substructure as a new Higgs search channel at the LHC
• Boosted objects: a probe of beyond the Standard Model physics
• Power Counting to Better Jet Observables
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Identification techniques for highly boosted W bosons that decay into hadrons
• Multivariate discrimination and the Higgs + W/Z search

Cited by in corpus (13)

• Classification without labels: Learning from mixed samples in high energy physics
• Extending the Bump Hunt with Machine Learning
• New Angles on Energy Correlation Functions
• Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions
• Pileup Mitigation with Machine Learning (PUMML)
• Taming modeling uncertainties with Mass Unspecific Supervised Tagging
• Machine learning approach to analyze heavy quark diffusion coefficient in relativistic heavy-ion collisions
• Double-charming Higgs identification using machine-learning assisted jet shapes
• Role of polarizations and spin-spin correlations of $W^{\prime }s$ in $e^{-}{e}^{+}\to W^{-}{W}^{+}$ at $\sqrt{s}=250$ GeV to probe anomalous $W^{-}{W}^{+}Z/\gamma$ couplings
• Investigating top tagging with Y${}_{\text{m}}$-Splitter and N-subjettiness
• Top quark physics in the Large Hadron Collider era
• Image-Based Jet Analysis
• Energy Flow in Particle Collisions