Anomaly Detection under Coordinate Transformations

Abstract

There is a growing need for machine learning-based anomaly detection strategies to broaden the search for Beyond-the-Standard-Model (BSM) physics at the Large Hadron Collider (LHC) and elsewhere. The first step of any anomaly detection approach is to specify observables and then use them to decide on a set of anomalous events. One common choice is to select events that have low probability density. It is a well-known fact that probability densities are not invariant under coordinate transformations, so the sensitivity can depend on the initial choice of coordinates. The broader machine learning community has recently connected coordinate sensitivity with anomaly detection and our goal is to bring awareness of this issue to the growing high energy physics literature on anomaly detection. In addition to analytical explanations, we provide numerical examples from simple random variables and from the LHC Olympics Dataset that show how using probability density as an anomaly score can lead to events being classified as anomalous or not depending on the coordinate frame.

10 pages, 6 figures

References in corpus (11)

• Classification without labels: Learning from mixed samples in high energy physics
• Extending the Bump Hunt with Machine Learning
• A generic anti-QCD jet tagger
• Anomaly detection in high-energy physics using a quantum autoencoder
• Autoencoders for Semivisible Jet Detection
• Transferability of Deep Learning Models in Searches for New Physics at Colliders
• Self-supervised Anomaly Detection for New Physics
• Learning new physics efficiently with nonparametric methods
• Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows
• Data-Directed Search for New Physics based on Symmetries of the SM
• Taming modeling uncertainties with Mass Unspecific Supervised Tagging

Cited by in corpus (10)

• High-dimensional and Permutation Invariant Anomaly Detection
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Anomalies, Representations, and Self-Supervision
• Combining Resonant and Tail-based Anomaly Detection
• Resonant Anomaly Detection with Multiple Reference Datasets
• Anomaly detection with flow-based fast calorimeter simulators
• Semi-visible jets, energy-based models, and self-supervision
• Non-resonant Anomaly Detection with Background Extrapolation
• Triggering Dark Showers with Conditional Dual Auto-Encoders
• 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