Learning to Classify from Impure Samples with High-Dimensional Data

Abstract

A persistent challenge in practical classification tasks is that labeled training sets are not always available. In particle physics, this challenge is surmounted by the use of simulations. These simulations accurately reproduce most features of data, but cannot be trusted to capture all of the complex correlations exploitable by modern machine learning methods. Recent work in weakly supervised learning has shown that simple, low-dimensional classifiers can be trained using only the impure mixtures present in data. Here, we demonstrate that complex, high-dimensional classifiers can also be trained on impure mixtures using weak supervision techniques, with performance comparable to what could be achieved with pure samples. Using weak supervision will therefore allow us to avoid relying exclusively on simulations for high-dimensional classification. This work opens the door to a new regime whereby complex models are trained directly on data, providing direct access to probe the underlying physics.

6 pages, 2 tables, 2 figures. v2: updated to match PRD version

References in corpus (8)

• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Classification without labels: Learning from mixed samples in high energy physics
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Energy flow polynomials: A complete linear basis for jet substructure
• 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

Cited by in corpus (53)

• Machine learning and the physical sciences
• ParticleNet: Jet Tagging via Particle Clouds
• The Machine Learning Landscape of Top Taggers
• Extending the Bump Hunt with Machine Learning
• QCD or What?
• 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
• Pulling Out All the Tops with Computer Vision and Deep Learning
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Uncovering latent jet substructure
• Autoencoders for unsupervised anomaly detection in high energy physics
• Modern Machine Learning and Particle Physics
• Jet Charge and Machine Learning
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• ABCDisCo: Automating the ABCD Method with Machine Learning
• 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
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Deep-Learning Jets with Uncertainties and More
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• INFERNO: Inference-Aware Neural Optimisation
• A Theory of Quark vs. Gluon Discrimination
• Per-Object Systematics using Deep-Learned Calibration
• Automating the Construction of Jet Observables with Machine Learning
• Mass Agnostic Jet Taggers
• Infrared Safety of a Neural-Net Top Tagging Algorithm
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Detecting an axion-like particle with machine learning at the LHC
• Electromagnetic Showers Beyond Shower Shapes
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• CapsNets Continuing the Convolutional Quest
• Boosting mono-jet searches with model-agnostic machine learning
• Disentangling Boosted Higgs Boson Production Modes with Machine Learning
• Identifying the relevant dependencies of the neural network response on characteristics of the input space
• Maximum performance of strange-jet tagging at hadron colliders
• Learning to Inflate
• Quark jet rates and quark/gluon discrimination in multi-jet final states
• Mixture-of-theories Training: Can We Find New Physics and Anomalies Better by Mixing Physical Theories?
• Searching for dark jets with displaced vertices using weakly supervised machine learning
• Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Variational Autoencoders for Jet Simulation
• Learning from Multiple Corrupted Sources, with Application to Learning from Label Proportions
• Strange Jet Tagging
• Classify the Higgs decays with the PFN and ParticleNet at electron-positron colliders
• Quark-versus-gluon tagging in CMS Open Data with CWoLa and TopicFlow
• Optimal event selection and categorization in high energy physics, Part 1: Signal discovery
• Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
• Application of Gene Expression Programming in Improving the Event Selection of the Semi-leptonic Top Quark Pair Process
• Machine Learning for New Physics Searches
• Energy Flow in Particle Collisions