Decorrelated Jet Substructure Tagging using Adversarial Neural Networks

Abstract

We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic uncertainties in background modeling while enhancing signal purity, resulting in improved discovery significance relative to existing taggers. The network is trained using an adversarial strategy, resulting in a tagger that learns to balance classification accuracy with decorrelation. As a benchmark scenario, we consider the case where large-radius jets originating from a boosted resonance decay are discriminated from a background of nonresonant quark and gluon jets. We show that in the presence of systematic uncertainties on the background rate, our adversarially-trained, decorrelated tagger considerably outperforms a conventionally trained neural network, despite having a slightly worse signal-background separation power. We generalize the adversarial training technique to include a parametric dependence on the signal hypothesis, training a single network that provides optimized, interpolatable decorrelated jet tagging across a continuous range of hypothetical resonance masses, after training on discrete choices of the signal mass.

References in corpus (10)

• 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
• Event generation with SHERPA 1.1
• Jet substructure as a new Higgs search channel at the LHC
• Boosted objects: a probe of beyond the Standard Model physics
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Parameterized Machine Learning for High-Energy Physics
• Power Counting to Better Jet Observables
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• Boosting low-mass hadronic resonances

Cited by in corpus (66)

• Machine learning and the physical sciences
• Deep Learning and its Application to LHC Physics
• 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
• Anomaly Detection for Resonant New Physics with Machine Learning
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• A generic anti-QCD jet tagger
• QCD or What?
• Simulation Assisted Likelihood-free Anomaly Detection
• What is the Machine Learning?
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• The Lund Jet Plane
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Variational Autoencoders for Anomalous Jet Tagging
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• DisCo Fever: Robust Networks Through Distance Correlation
• Machine Learning Uncertainties with Adversarial Neural Networks
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Bump Hunting in Latent Space
• Exploring the Space of Jets with CMS Open Data
• 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
• Uncertainty Aware Learning for High Energy Physics
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Equivariant Energy Flow Networks for Jet Tagging
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Measurements of Higgs Bosons Decaying to Bottom Quarks from Vector Boson Fusion Production with the ATLAS Experiment at $\sqrt{s}=$ 13 TeV
• Automating the Construction of Jet Observables with Machine Learning
• Mass Agnostic Jet Taggers
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
• A Cautionary Tale of Decorrelating Theory Uncertainties
• LHC analysis-specific datasets with Generative Adversarial Networks
• Dedicated Strategies for Triboson Signals from Cascade Decays of Vector Resonances
• Reducing the dependence of the neural network function to systematic uncertainties in the input space
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• The importance of calorimetry for highly-boosted jet substructure
• Jet grooming through reinforcement learning
• Classification and Recovery of Radio Signals from Cosmic Ray Induced Air Showers with Deep Learning
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Optimal statistical inference in the presence of systematic uncertainties using neural network optimization based on binned Poisson likelihoods with nuisance parameters
• Learning to Identify Semi-Visible Jets
• Learning Multivariate New Physics
• Charm-quark Yukawa Coupling in $h\to c\bar{c}\gamma$ at LHC
• Enhancing searches for resonances with machine learning and moment decomposition
• Dijet and electroweak limits on a $Z^{\prime }$ boson coupled to quarks
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Preserving physically important variables in optimal event selections: A case study in Higgs physics
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• Machine learning classification: case of Higgs boson CP state in H to tau tau decay at LHC
• Double-charming Higgs identification using machine-learning assisted jet shapes
• Meta-learning and data augmentation for mass-generalised jet taggers
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
• Riemannian Data preprocessing in Machine Learning to focus on QCD color structure
• PAIReD jet: A multi-pronged resonance tagging strategy across all Lorentz boosts
• Decorrelation using Optimal Transport
• Designing Observables for Measurements with Deep Learning
• Image-Based Jet Analysis
• Optimal event selection and categorization in high energy physics, Part 1: Signal discovery