Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection

Abstract

Anomaly detection techniques are growing in importance at the Large Hadron Collider (LHC), motivated by the increasing need to search for new physics in a model-agnostic way. In this work, we provide a detailed comparative study between a well-studied unsupervised method called the autoencoder (AE) and a weakly-supervised approach based on the Classification Without Labels (CWoLa) technique. We examine the ability of the two methods to identify a new physics signal at different cross sections in a fully hadronic resonance search. By construction, the AE classification performance is independent of the amount of injected signal. In contrast, the CWoLa performance improves with increasing signal abundance. When integrating these approaches with a complete background estimate, we find that the two methods have complementary sensitivity. In particular, CWoLa is effective at finding diverse and moderately rare signals while the AE can provide sensitivity to very rare signals, but only with certain topologies. We therefore demonstrate that both techniques are complementary and can be used together for anomaly detection at the LHC.

39 pages, 17 figures

References in corpus (20)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Classification without labels: Learning from mixed samples in high energy physics
• Extending the Bump Hunt with Machine Learning
• A generic anti-QCD jet tagger
• Simulation Assisted Likelihood-free Anomaly Detection
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Multivariate discrimination and the Higgs + W/Z search
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• A Living Review of Machine Learning for Particle Physics
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Bump Hunting in Latent Space
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Unsupervised clustering for collider physics
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Transferability of Deep Learning Models in Searches for New Physics at Colliders
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Unsupervised in-distribution anomaly detection of new physics through conditional density estimation
• Decoding Dark Matter Substructure without Supervision
• Unsupervised Event Classification with Graphs on Classical and Photonic Quantum Computers
• Uncovering hidden patterns in collider events with Bayesian probabilistic models

Cited by in corpus (25)

• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Better Latent Spaces for Better Autoencoders
• Bump Hunting in Latent Space
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Resonant anomaly detection without background sculpting
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Symmetries, Safety, and Self-Supervision
• Quantum Anomaly Detection for Collider Physics
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• Anomaly Detection under Coordinate Transformations
• Anomaly detection from mass unspecific jet tagging
• High-dimensional and Permutation Invariant Anomaly Detection
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Event-based anomaly detection for new physics searches at the LHC using machine learning
• Combining Resonant and Tail-based Anomaly Detection
• Searching for dark jets with displaced vertices using weakly supervised machine learning
• Deep learning techniques for Imaging Air Cherenkov Telescopes
• Non-resonant Anomaly Detection with Background Extrapolation
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Unsupervised and lightly supervised learning in particle physics
• Detecting New Physics as Novelty -- Complementarity Matters
• Preserving New Physics while Simultaneously Unfolding All Observables
• Weakly supervised anomaly detection with event-level variables