Eur. Phys. J. C (2021) 81: 617
https://doi.org/10.1140/epjc/s10052-021-09389-x

Regular Article - Theoretical Physics

Comparing weak- and unsupervised methods for resonant anomaly detection

¹ SLAC National Accelerator Laboratory, Stanford University, 94309, Stanford, CA, USA
² Instituto de Física Teórica, IFT-UAM/CSIC, Universidad Autónoma de Madrid, 28049, Madrid, Spain
³ Physics Division, Lawrence Berkeley National Laboratory, 94720, Berkeley, CA, USA
⁴ Berkeley Institute for Data Science, University of California, 94720, Berkeley, CA, USA
⁵ NHETC, Department of Physics and Astronomy, Rutgers University, 08854, Piscataway, NJ, USA

^b pmartin.ramiro@predoc.uam.es

Received: 16 April 2021
Accepted: 25 June 2021
Published online: 15 July 2021

Abstract

Anomaly detection techniques are growing in importance at the Large Hadron Collider (LHC), motivated by the increasing need to search for new physics in a model-agnostic way. In this work, we provide a detailed comparative study between a well-studied unsupervised method called the autoencoder (AE) and a weakly-supervised approach based on the Classification Without Labels (CWoLa) technique. We examine the ability of the two methods to identify a new physics signal at different cross sections in a fully hadronic resonance search. By construction, the AE classification performance is independent of the amount of injected signal. In contrast, the CWoLa performance improves with increasing signal abundance. When integrating these approaches with a complete background estimate, we find that the two methods have complementary sensitivity. In particular, CWoLa is effective at finding diverse and moderately rare signals while the AE can provide sensitivity to very rare signals, but only with certain topologies. We therefore demonstrate that both techniques are complementary and can be used together for anomaly detection at the LHC.