Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC

TL;DR

This paper introduces a novel anomaly detection method combining likelihood and out-of-distribution models to identify rare or different events in particle physics collider data, demonstrating strong performance on simulated and unknown signals.

Contribution

It presents a new ensemble-based anomaly scoring approach that integrates models for rarity and differentness, applicable to collider data and potentially other fields.

Findings

Performed well on simulated Standard Model data

Successfully detected hypothetical signals in multiple channels

Applicable to various datasets beyond particle physics

Abstract

We propose a new method to define anomaly scores and apply this to particle physics collider events. Anomalies can be either rare, meaning that these events are a minority in the normal dataset, or different, meaning they have values that are not inside the dataset. We quantify these two properties using an ensemble of One-Class Deep Support Vector Data Description models, which quantifies differentness, and an autoregressive flow model, which quantifies rareness. These two parameters are then combined into a single anomaly score using different combination algorithms. We train the models using a dataset containing only simulated collisions from the Standard Model of particle physics and test it using various hypothetical signals in four different channels and a secret dataset where the signals are unknown to us. The anomaly detection method described here has been evaluated in a summary paper [1] where it performed very well compared to a large number of other methods. The method is simple to implement and is applicable to other datasets in other fields as well.