Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
This work addresses the problem of discovering new particles in high-energy physics, offering incremental improvements by leveraging more background information for robustness.
The paper tackled anomaly detection in particle physics by using representation learning from multiple background types and generalizing decorrelation to this setting, resulting in improved detection performance on a high-dimensional dataset from the Large Hadron Collider.
Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation learning from multiple background types, thus taking advantage of more information to improve estimation of what is relevant for detection. Second, we generalize decorrelation to the multi-background setting, thus directly enforcing a more complete definition of robustness for anomaly detection. We demonstrate the benefit of the proposed robust multi-background anomaly detection algorithms on a high-dimensional dataset of particle decays at the Large Hadron Collider.