Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data

Abstract

There has been substantial progress in applying machine learning techniques to classification problems in collider and jet physics. But as these techniques grow in sophistication, they are becoming more sensitive to subtle features of jets that may not be well modeled in simulation. Therefore, relying on simulations for training will lead to sub-optimal performance in data, but the lack of true class labels makes it difficult to train on real data. To address this challenge we introduce a new approach, called Tag N' Train (TNT), that can be applied to unlabeled data that has two distinct sub-objects. The technique uses a weak classifier for one of the objects to tag signal-rich and background-rich samples. These samples are then used to train a stronger classifier for the other object. We demonstrate the power of this method by applying it to a dijet resonance search. By starting with autoencoders trained directly on data as the weak classifiers, we use TNT to train substantially improved classifiers. We show that Tag N' Train can be a powerful tool in model-agnostic searches and discuss other potential applications.

20 pages, 7 figures. Updated to match version accepted in JHEP. Contains new background estimation method for TNT on non-resonant signals, more detailed significance comparisons between methods and an appendix illustrating why repeatedly training without using TNT does not work

References in corpus (46)

• The anti-k_t jet clustering algorithm
• FastJet user manual
• Dispelling the N^3 myth for the Kt jet-finder
• Identifying Boosted Objects with N-subjettiness
• Muon reconstruction performance of the ATLAS detector in proton--proton collision data at $\sqrt{s}$=13 TeV
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Anomaly Detection with Density Estimation
• Classification without labels: Learning from mixed samples in high energy physics
• Deep learning in color: towards automated quark/gluon jet discrimination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Searching for New Physics with Deep Autoencoders
• Anomaly Detection for Resonant New Physics with Machine Learning
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• Deep-learned Top Tagging with a Lorentz Layer
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Improving Variational Inference with Inverse Autoregressive Flow
• How to GAN LHC Events
• A generic anti-QCD jet tagger
• QCD or What?
• Simulation Assisted Likelihood-free Anomaly Detection
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Guiding New Physics Searches with Unsupervised Learning
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• Variational Autoencoders for New Physics Mining at the Large Hadron Collider
• QCD-Aware Recursive Neural Networks for Jet Physics
• Uncovering latent jet substructure
• Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure
• Learning to Pivot with Adversarial Networks
• DisCo Fever: Robust Networks Through Distance Correlation
• Model-Independent and Quasi-Model-Independent Search for New Physics at CDF
• The experimental status of direct searches for exotic physics beyond the standard model at the Large Hadron Collider
• A general search for new phenomena in ep scattering at HERA
• A strategy for a general search for new phenomena using data-derived signal regions and its application within the ATLAS experiment
• A Quasi-Model-Independent Search for New Physics at Large Transverse Momentum
• A Quasi-Model-Independent Search for New High p_T Physics at DZero
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Mass Agnostic Jet Taggers
• The motivation and status of two-body resonance decays after the LHC Run 2 and beyond

Cited by in corpus (53)

• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Autoencoders for unsupervised anomaly detection in high energy physics
• Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
• Better Latent Spaces for Better Autoencoders
• 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
• Casting a graph net to catch dark showers
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• FETA: Flow-Enhanced Transportation for Anomaly Detection
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• Learning new physics efficiently with nonparametric methods
• The Interplay of Machine Learning--based Resonant Anomaly Detection Methods
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• What's Anomalous in LHC Jets?
• Anomaly Detection under Coordinate Transformations
• Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Anomaly detection from mass unspecific jet tagging
• High-dimensional and Permutation Invariant Anomaly Detection
• Boosting mono-jet searches with model-agnostic machine learning
• Anomalies, Representations, and Self-Supervision
• Data-Directed Search for New Physics based on Symmetries of the SM
• Anomaly Awareness
• Combining Resonant and Tail-based Anomaly Detection
• GAN-AE : An anomaly detection algorithm for New Physics search in LHC data
• Enhancing the hunt for new phenomena in dijet final-states using anomaly detection filters at the High-Luminosity Large Hadron Collider
• Resonant Anomaly Detection with Multiple Reference Datasets
• Model selection and signal extraction using Gaussian Process regression
• Searching for dark jets with displaced vertices using weakly supervised machine learning
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Non-resonant Anomaly Detection with Background Extrapolation
• Variational Autoencoders for Jet Simulation
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Unsupervised and lightly supervised learning in particle physics
• Exotic diboson $Z^{\prime }$ decays in the U$\mu \nu$SSM
• Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
• Detecting New Physics as Novelty -- Complementarity Matters
• Learning New Physics from an Imperfect Machine
• Preserving New Physics while Simultaneously Unfolding All Observables
• Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
• Weakly supervised anomaly detection with event-level variables
• Graph theory inspired anomaly detection at the LHC
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure