English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Anomaly detection techniques are growing in importance at the Large HadronCollider (LHC), motivated by the increasing need to search for new physics in amodel-agnostic way. In this work, we provide a detailed comparative studybetween a well-studied unsupervised method called the autoencoder (AE) and aweakly-supervised approach based on the Classification Without Labels (CWoLa)technique. We examine the ability of the two methods to identify a new physicssignal at different cross sections in a fully hadronic resonance search. Byconstruction, the AE classification performance is independent of the amount ofinjected signal. In contrast, the CWoLa performance improves with increasingsignal abundance. When integrating these approaches with a complete backgroundestimate, we find that the two methods have complementary sensitivity. Inparticular, CWoLa is effective at finding diverse and moderately rare signalswhile the AE can provide sensitivity to very rare signals, but only withcertain topologies. We therefore demonstrate that both techniques arecomplementary and can be used together for anomaly detection at the LHC.

Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection