Resonant anomaly detection without background sculpting

Journal Article · 09 June 2023 · Physical Review. D.

DOI: https://doi.org/10.1103/physrevd.107.114012 · OSTI ID:1984535

Hallin, Anna  ^[1]; Kasieczka, Gregor  ^[2]; Quadfasel, Tobias  ^[3]; Shih, David  ^[1]; Sommerhalder, Manuel  ^[3]

---

1. Rutgers University, Piscataway, NJ (United States)
2. University of Hamburg (Germany); Center for Data and Computing in Natural Sciences (CDCS), Hamburg (Germany)
3. University of Hamburg (Germany)

We introduce a new technique named latent CATHODE (LaCATHODE) for performing “enhanced bump hunts,” a type of resonant anomaly search that combines conventional one-dimensional bump hunts with a model-agnostic anomaly score in an auxiliary feature space where potential signals could also be localized. The main advantage of LaCATHODE over existing methods is that it provides an anomaly score that is well behaved when evaluating it beyond the signal region, which is essential to prevent the sculpting of background distributions in the bump hunt. LaCATHODE accomplishes this by constructing the anomaly score directly in the latent space learned by a conditional normalizing flow trained on sideband regions. We demonstrate the superior stability and comparable performance of LaCATHODE for enhanced bump hunting in an illustrative toy example as well as on the LHC Olympics R&D dataset.

• Research Organization: Rutgers Univ., Piscataway, NJ (United States)
• Sponsoring Organization: USDOE Office of Science (SC); German Federal Ministry of Education and Research (BMBF); USDOE
• Grant/Contract Number: SC0010008; 05H21GUCC1; DOE-SC0010008
• OSTI ID: 1984535
• Alternate ID(s): OSTI ID: 2419970
• Journal Information: Physical Review. D., Vol. 107, Issue 11; ISSN 2470-0010
• Publisher: American Physical Society (APS)Copyright Statement
• Country of Publication: United States
• Language: English