Classification without labels: Learning from mixed samples in high energy physics

Abstract

Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this paper, we introduce the paradigm of classification without labels (CWoLa) in which a classifier is trained to distinguish statistical mixtures of classes, which are common in collider physics. Crucially, neither individual labels nor class proportions are required, yet we prove that the optimal classifier in the CWoLa paradigm is also the optimal classifier in the traditional fully-supervised case where all label information is available. After demonstrating the power of this method in an analytical toy example, we consider a realistic benchmark for collider physics: distinguishing quark- versus gluon-initiated jets using mixed quark/gluon training samples. More generally, CWoLa can be applied to any classification problem where labels or class proportions are unknown or simulations are unreliable, but statistical mixtures of the classes are available.

18 pages, 5 figures; v2: intro extended and references added; v3: additional discussion to match JHEP version

References in corpus (42)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• The anti-k_t jet clustering algorithm
• A Brief Introduction to PYTHIA 8.1
• FastJet user manual
• Jet substructure as a new Higgs search channel at the LHC
• Soft Drop
• Jet Trimming
• Identification of b-quark jets with the CMS experiment
• Towards an understanding of jet substructure
• Performance of $b$-Jet Identification in the ATLAS Experiment
• Jet substructure as a new Higgs search channel at the LHC
• Recombination Algorithms and Jet Substructure: Pruning as a Tool for Heavy Particle Searches
• Techniques for improved heavy particle searches with jet substructure
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Jet Shapes and Jet Algorithms in SCET
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Substructure of high-p_T Jets at the LHC
• Event Shape/Energy Flow Correlations
• Gaining (Mutual) Information about Quark/Gluon Discrimination
• Quark and Gluon Tagging at the LHC
• Jet Shapes with the Broadening Axis
• Les Houches 2015: Physics at TeV Colliders Standard Model Working Group Report
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Systematics of quark/gluon tagging
• Quark and Gluon Jet Substructure
• Factorization for groomed jet substructure beyond the next-to-leading logarithm
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• Light-quark and gluon jet discrimination in pp collisions at $\sqrt{s}$ = 7 TeV with the ATLAS detector
• Pileup Mitigation with Machine Learning (PUMML)
• Identification techniques for highly boosted W bosons that decay into hadrons
• Jet Observables Without Jet Algorithms
• How Much Information is in a Jet?
• Weakly Supervised Classification in High Energy Physics
• Identification of boosted, hadronically decaying W bosons and comparisons with ATLAS data taken at $\sqrt{s}=8$ TeV
• Measurement of the charged-particle multiplicity inside jets from $\sqrt{s}=8$ TeV $pp$ collisions with the ATLAS detector
• Pure Samples of Quark and Gluon Jets at the LHC
• Precision physics with pile-up insensitive observables
• Playing Tag with ANN: Boosted Top Identification with Pattern Recognition

Cited by in corpus (154)

• Machine learning and the physical sciences
• ParticleNet: Jet Tagging via Particle Clouds
• 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
• Searching for New Physics with Deep Autoencoders
• Searching for long-lived particles beyond the Standard Model at the Large Hadron Collider
• Anomaly Detection for Resonant New Physics with Machine Learning
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Extending the Bump Hunt with Machine Learning
• QCD or What?
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Energy flow polynomials: A complete linear basis for jet substructure
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Pulling Out All the Tops with Computer Vision and Deep Learning
• The Lund Jet Plane
• Guiding New Physics Searches with Unsupervised Learning
• Solving differential equations with neural networks: Applications to the calculation of cosmological phase transitions
• QCD-Aware Recursive Neural Networks for Jet Physics
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Uncovering latent jet substructure
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Learning to Classify from Impure Samples with High-Dimensional Data
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Autoencoders for unsupervised anomaly detection in high energy physics
• On the Topic of Jets: Disentangling Quarks and Gluons at Colliders
• Boosting $H\to b\bar{b}$ with Machine Learning
• Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Novel Jet Observables from Machine Learning
• Machine Learning Uncertainties with Adversarial Neural Networks
• Modern Machine Learning and Particle Physics
• Jet Charge and Machine Learning
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Bump Hunting in Latent Space
• Machine Learning for Anomaly Detection in Particle Physics
• (Machine) Learning to Do More with Less
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Quark-Gluon Tagging: Machine Learning vs Detector
• An operational definition of quark and gluon jets
• Deep-Learning Jets with Uncertainties and More
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Casting a graph net to catch dark showers
• Learning the latent structure of collider events
• Mapping Machine-Learned Physics into a Human-Readable Space
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Unsupervised clustering for collider physics
• CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals
• INFERNO: Inference-Aware Neural Optimisation
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• A Theory of Quark vs. Gluon Discrimination
• Symmetries, Safety, and Self-Supervision
• FETA: Flow-Enhanced Transportation for Anomaly Detection
• Measurement of the $\mathrm{t}\bar{\mathrm{t}}\mathrm{b}\bar{\mathrm{b}}$ production cross section in the all-jet final state in pp collisions at $\sqrt{s}=$ 13 TeV
• Reweighting a parton shower using a neural network: the final-state case
• Per-Object Systematics using Deep-Learned Calibration
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• Unsupervised Hadronic SUEP at the LHC
• Anomalous Jet Identification via Sequence Modeling
• Automating the Construction of Jet Observables with Machine Learning
• Jet angularity measurements for single inclusive jet production
• Infrared Safety of a Neural-Net Top Tagging Algorithm
• Self-supervised Anomaly Detection for New Physics
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Opening the black box of neural nets: case studies in stop/top discrimination
• The Interplay of Machine Learning--based Resonant Anomaly Detection Methods
• Disentangling Quarks and Gluons with CMS Open Data
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• What's Anomalous in LHC Jets?
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Triggering on Emerging Jets
• Explainable machine learning of the underlying physics of high-energy particle collisions
• Anomaly Detection under Coordinate Transformations
• Investigating the Topology Dependence of Quark and Gluon Jets
• Deep learning for the R-parity violating supersymmetry searches at the LHC
• Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• High-dimensional and Permutation Invariant Anomaly Detection
• CapsNets Continuing the Convolutional Quest
• Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows
• Boosting mono-jet searches with model-agnostic machine learning
• A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Solving Key Challenges in Collider Physics with Foundation Models
• Invisible Higgs search through Vector Boson Fusion: A deep learning approach
• Data-Directed Search for New Physics based on Symmetries of the SM
• GPU coprocessors as a service for deep learning inference in high energy physics
• Neural Embedding: Learning the Embedding of the Manifold of Physics Data
• Anomalies, Representations, and Self-Supervision
• Anomaly Awareness
• Combining Resonant and Tail-based Anomaly Detection
• Gamma/Hadron Separation with the HAWC Observatory
• Identifying the relevant dependencies of the neural network response on characteristics of the input space
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Production of tau tau jj final states at the LHC and the TauSpinner algorithm: the spin-2 case
• Quark jet rates and quark/gluon discrimination in multi-jet final states
• Resonant Anomaly Detection with Multiple Reference Datasets
• Learning to Inflate
• Maximum performance of strange-jet tagging at hadron colliders
• Mixture-of-theories Training: Can We Find New Physics and Anomalies Better by Mixing Physical Theories?
• Towards a method to anticipate dark matter signals with deep learning at the LHC
• A Quantum Algorithm for Model-Independent Searches for New Physics
• Machine Learning on data with sPlot background subtraction
• Class Imbalance Techniques for High Energy Physics
• Searching for dark jets with displaced vertices using weakly supervised machine learning
• Is infrared-collinear safe information all you need for jet classification?
• Topic Model for four-top at the LHC
• Learning to Isolate Muons
• Accuracy versus precision in boosted top tagging with the ATLAS detector
• Weakly-Supervised Anomaly Detection in the Milky Way
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• Non-resonant Anomaly Detection with Background Extrapolation
• Variational Autoencoders for Jet Simulation
• A machine learning-based methodology for pulse classification in dual-phase xenon time projection chambers
• Unsupervised and lightly supervised learning in particle physics
• Isolating Unisolated Upsilons with Anomaly Detection in CMS Open Data
• Searching for periodic signals in kinematic distributions using continuous wavelet transforms
• Finding Wombling Boundaries in LHC Data with Voronoi and Delaunay Tessellations
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• Triggering Dark Showers with Conditional Dual Auto-Encoders
• Strange Jet Tagging
• Classify the Higgs decays with the PFN and ParticleNet at electron-positron colliders
• Semi-supervised permutation invariant particle-level anomaly detection
• How much joint resummation do we need?
• Improving Heavy Dijet Resonance Searches Using Jet Substructure at the LHC
• Quark-versus-gluon tagging in CMS Open Data with CWoLa and TopicFlow
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Weakly supervised anomaly detection for resonant new physics in the dijet final state using proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Quirk SUEP
• Searching for New Physics in Hadronic Final States with Run 2 Proton-Proton Collision Data at the LHC
• New Methods and Datasets for Group Anomaly Detection From Fundamental Physics
• Detecting New Physics as Novelty -- Complementarity Matters
• Inferring correlated distributions: boosted top jets
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
• Learning New Physics from an Imperfect Machine
• Energy Flow in Particle Collisions
• Optimal event selection and categorization in high energy physics, Part 1: Signal discovery
• Graph theory inspired anomaly detection at the LHC
• Experimental Impact of Jet Fragmentation Reference Frames At Particle Colliders
• Strong CWoLa: Binary Classification Without Background Simulation
• Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
• Noisy Labels for Weakly Supervised Gamma Hadron Classification
• Deficit hawks: robust new physics searches with unknown backgrounds
• Weakly supervised anomaly detection with event-level variables
• Machine Learning for New Physics Searches