Title: Comparing weak- and unsupervised methods for resonant anomaly detection

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.

Authors:

Collins, Jack H.; Martín-Ramiro, Pablo ;

• Search DOE PAGES for author "Martín-Ramiro, Pablo"
• Search DOE PAGES for ORCID "0000-0001-5858-5783"

Nachman, Benjamin; Shih, David

Publication Date:

Thu Jul 15 00:00:00 EDT 2021

Research Org.:

SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Org.:

USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Science (SC), High Energy Physics (HEP)

OSTI Identifier:

1808209

Alternate Identifier(s):

OSTI ID: 1819743; OSTI ID: 1820604

Grant/Contract Number:  

AC02-05CH11231; AC02-76SF00515; DOE-SC0010008

Resource Type:

Published Article

Journal Name:

European Physical Journal. C, Particles and Fields

Additional Journal Information:

Journal Name: European Physical Journal. C, Particles and Fields Journal Volume: 81 Journal Issue: 7; Journal ID: ISSN 1434-6044

Publisher:

Springer Science + Business Media

Country of Publication:

Germany

Language:

English

Subject:

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS