Anomaly detection methods improve identifying rare events at HL-LHC
Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC
Artificial Intelligence
Summary
At the Large Hadron Collider, scientists look for unusual particle collision events that might show new physics beyond the Standard Model. The authors study neural network techniques to find these rare events using simplified data representations. They show that methods trained with labeled simulations perform better at spotting anomalies than those without labels. They also develop a new way to explain which physical measurements make these events stand out, helping to understand and follow up on potential discoveries.
What this means in practice
- •For particle physics experiment teams: Detect rare collision events more effectively and interpret their physical characteristics during data analysis at high-luminosity collider runs.
Authors
Donatella Genovese, Philip Ploner, Simone Scardapane, Stefano Giagu, Thea Klaeboe Aarrestad
Abstract
Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic strategies for new-physics searches at the Large Hadron Collider. Searching for rare events in learned low-dimensional representations removes the need to commit to hand-crafted observables a priori, but sacrifices the immediate physical interpretation those observables provide. For anomaly detection to enter a discovery pipeline, flagged events must therefore be diagnosed locally, both to distinguish potential new physics from mismodeling or detector effects and to identify observables for targeted follow-up searches. We evaluate supervised and self-supervised neural embedding strategies on COLLIDE-2V, a 750-million-event dataset simulated under realistic High-Luminosity LHC conditions, using the reconstruction error of an autoencoder trained in the learned latent space as the anomaly score. Across the configurations and benchmark signals considered, supervised objectives, which exploit simulation process labels during training, generally outperform their self-supervised counterparts and, in their best configurations, improve on an autoencoder trained directly on kinematic features, raising the signal efficiency at 10% background acceptance on all held-out processes. We further introduce a local diagnostic pipeline that fits a Gaussian Mixture Model to the SM latent space, profiles each component through high-level observables without process labels, localizes the flagged events, and ranks observables by their local discriminating power. The ranking recovers the defining kinematics of the held-out processes, while correlating the anomaly score with the same observables quantifies how closely the score tracks them, revealing cases where the most discriminating observable is not the one the score follows most closely.