Self-supervised Anomaly Detection for New Physics

Abstract

We investigate a method of model-agnostic anomaly detection through studying jets, collimated sprays of particles produced in high-energy collisions. We train a transformer neural network to encode simulated QCD "event space" dijets into a low-dimensional "latent space" representation. We optimize the network using the self-supervised contrastive loss, which encourages the preservation of known physical symmetries of the dijets. We then train a binary classifier to discriminate a BSM resonant dijet signal from a QCD dijet background both in the event space and the latent space representations. We find the classifier performances on the event and latent spaces to be comparable. We finally perform an anomaly detection search using a weakly supervised bump hunt on the latent space dijets, finding again a comparable performance to a search run on the physical space dijets. This opens the door to using low-dimensional latent representations as a computationally efficient space for resonant anomaly detection in generic particle collision events.

13 pages, 12 figures. minor updates, v2 (published version)

References in corpus (4)

• PYTHIA 6.4 Physics and Manual
• An Introduction to PYTHIA 8.2
• Classification without labels: Learning from mixed samples in high energy physics
• Extending the Bump Hunt with Machine Learning

Cited by in corpus (18)

• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• Anomaly Detection under Coordinate Transformations
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Solving Key Challenges in Collider Physics with Foundation Models
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Anomalies, Representations, and Self-Supervision
• Neural Embedding: Learning the Embedding of the Manifold of Physics 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
• Semi-visible jets, energy-based models, and self-supervision
• Non-resonant Anomaly Detection with Background Extrapolation
• Unsupervised and lightly supervised learning in particle physics
• Learning the Simplicity of Scattering Amplitudes
• Triggering Dark Showers with Conditional Dual Auto-Encoders
• Machine Learning Techniques for Intermediate Mass Gap Lepton Partner Searches at the Large Hadron Collider
• Semi-supervised permutation invariant particle-level anomaly detection
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC