Semi-supervised permutation invariant particle-level anomaly detection

TL;DR

This paper introduces a semi-supervised, permutation-invariant anomaly detection method for collider data that effectively identifies potential new physics signals using particle-level inputs.

Contribution

It presents a novel autoencoder-based architecture that encodes variable particle inputs into permutation-invariant representations for anomaly detection.

Findings

Effective discrimination between different new physics models

Permutation invariance improves detection robustness

Good performance on simulated collider data

Abstract

The development of analysis methods to distinguish potential beyond the Standard Model phenomena in a model-agnostic way can significantly enhance the discovery reach in collider experiments. However, the typical machine learning (ML) algorithms employed for this task require fixed length and ordered inputs that break the natural permutation invariance in collision events. To address this, a semi-supervised anomaly detection tool is presented that takes a variable number of particle-level inputs and leverages a signal model to encode this information into a permutation invariant, event-level representation via supervised training with a Particle Flow Network (PFN). Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. Performance of the ANTELOPE architecture is evaluated on simulated samples of hadronic processes in a high energy collider experiment, showing good capability to distinguish disparate models of new physics.