DisCo Fever: Robust Networks Through Distance Correlation

Abstract

While deep learning has proven to be extremely successful at supervised classification tasks at the LHC and beyond, for practical applications, raw classification accuracy is often not the only consideration. One crucial issue is the stability of network predictions, either versus changes of individual features of the input data, or against systematic perturbations. We present a new method based on a novel application of "distance correlation" (DisCo), a measure quantifying non-linear correlations, that achieves equal performance to state-of-the-art adversarial decorrelation networks but is much simpler and more stable to train. To demonstrate the effectiveness of our method, we carefully recast a recent ATLAS study of decorrelation methods as applied to boosted, hadronic W-tagging. We also show the feasibility of DisCo regularization for more powerful convolutional neural networks, as well as for the problem of hadronic top tagging.

arXiv comment9 pages, v2: essentially the journal version (refs added, typos fixed, minor improvements)

References in corpus (52)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The anti-k_t jet clustering algorithm
• A Brief Introduction to PYTHIA 8.1
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Measuring and testing dependence by correlation of distances
• Identifying Boosted Objects with N-subjettiness
• Brownian distance covariance
• Jet Trimming
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• MINE: Mutual Information Neural Estimation
• ParticleNet: Jet Tagging via Particle Clouds
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Power Counting to Better Jet Observables
• Deep-learned Top Tagging with a Lorentz Layer
• Learning in Implicit Generative Models
• What is the Machine Learning?
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• QCD-Aware Recursive Neural Networks for Jet Physics
• Uncovering latent jet substructure
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• Boosting $H\to b\bar{b}$ with Machine Learning
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• Identification of boosted, hadronically decaying W bosons and comparisons with ATLAS data taken at $\sqrt{s}=8$ TeV
• Search for pair production of vector-like quarks in the fully hadronic final state
• Machine Learning Uncertainties with Adversarial Neural Networks
• Jet Charge and Machine Learning
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Search for direct top squark pair production in events with one lepton, jets, and missing transverse momentum at 13 TeV with the CMS experiment
• Quark-Gluon Tagging: Machine Learning vs Detector
• Search for pair production of heavy vector-like quarks decaying into hadronic final states in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• uBoost: A boosting method for producing uniform selection efficiencies from multivariate classifiers
• Boosted $W/Z$ Tagging with Jet Charge and Deep Learning
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Convolved Substructure: Analytically Decorrelating Jet Substructure Observables
• Mass Agnostic Jet Taggers
• Identification of high transverse momentum top quarks in $pp$ collisions at $\sqrt{s}$ = 8 TeV with the ATLAS detector
• Jet Constituents for Deep Neural Network Based Top Quark Tagging
• Reports of My Demise Are Greatly Exaggerated: $N$-subjettiness Taggers Take On Jet Images
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Jet-Parton Assignment in ttH Events using Deep Learning
• Reducing the dependence of the neural network function to systematic uncertainties in the input space
• CapsNets Continuing the Convolutional Quest
• An artificial neural network based $b$ jet identification algorithm at the CDF Experiment
• Preserving physically important variables in optimal event selections: A case study in Higgs physics
• Correlational Neural Networks

Cited by in corpus (43)

• Anomaly Detection with Density Estimation
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Variational Autoencoders for Anomalous Jet Tagging
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Bump Hunting in Latent Space
• Machine Learning for Anomaly Detection in Particle Physics
• 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
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Equivariant Energy Flow Networks for Jet Tagging
• A neural simulation-based inference approach for characterizing the Galactic Center $\gamma$-ray excess
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Dark sector searches with the CMS experiment
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Search for R-parity violating supersymmetry in a final state containing leptons and many jets with the ATLAS experiment using $\sqrt{s}=13$ TeV proton-proton collision data
• 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
• Search for heavy Higgs bosons with flavour-violating couplings in multi-lepton plus $b$-jets final states in $pp$ collisions at 13 TeV with the ATLAS detector
• Enhancing searches for resonances with machine learning and moment decomposition
• GAN-AE : An anomaly detection algorithm for New Physics search in LHC data
• Search for long-lived particles using displaced vertices and missing transverse momentum in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Interpretable Uncertainty Quantification in AI for HEP
• Meta-learning and data augmentation for mass-generalised jet taggers
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging
• Deeply Learned Preselection of Higgs Dijet Decays at Future Lepton Colliders
• Riemannian Data preprocessing in Machine Learning to focus on QCD color structure
• Decorrelation using Optimal Transport
• PAIReD jet: A multi-pronged resonance tagging strategy across all Lorentz boosts
• Robust Distance Covariance
• Observation of the Singly Cabibbo-Suppressed Decay ${\Lambda }_c^{+}\to p{\pi }^0$
• Evidence for the dimuon decay of the Higgs boson in pp collisions with the ATLAS detector
• Designing Observables for Measurements with Deep Learning
• A search for dark matter produced in association with a dark Higgs boson decaying into a Higgs boson pair in 3$b$ or 4$b$ final states using $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Image-Based Jet Analysis
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Enhancing generalization in high energy physics using white-box adversarial attacks
• Search for the radiative leptonic decay $D^{+}\to \gamma e^{+}{\nu }_e$ using Deep Learning
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features