High-dimensional Anomaly Detection with Radiative Return in $e^{+}e^{-}$ Collisions

TL;DR

This paper demonstrates that machine learning techniques, specifically classification without labels combined with deep sets neural networks, can effectively detect new particles in $e^{+}e^{-}$ collider radiative return events, even with imperfect training data.

Contribution

It introduces a novel application of weakly supervised learning with deep sets neural networks for anomaly detection in $e^{+}e^{-}$ collisions, enhancing sensitivity to new particles.

Findings

Machine learning achieves sensitivity to new particles in radiative return events.

Deep sets neural networks effectively incorporate variable-dimensional data.

Discussion on experimental detector design implications.

Abstract

Experiments at a future $e^{+}e^{-}$ collider will be able to search for new particles with masses below the nominal centre-of-mass energy by analyzing collisions with initial-state radiation (radiative return). We show that machine learning methods that use imperfect or missing training labels can achieve sensitivity to generic new particle production in radiative return events. In addition to presenting an application of the classification without labels (CWoLa) search method in $e^{+}e^{-}$ collisions, our study combines weak supervision with variable-dimensional information by deploying a deep sets neural network architecture. We have also investigated some of the experimental aspects of anomaly detection in radiative return events and discuss these in the context of future detector design.