How to pick the best anomaly detector?
Physical Review D · 16.07.2026 · 114 (1)
DOI: 10.1103/9kcn-slvt ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review D, online erschienen am 16.07.2026. Verfasst von Marie Hein und 5 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, U.S. Department of Energy, RWTH Aachen University.
Abstract (Originalsprache)
Anomaly detection has the potential to discover new physics in unexplored regions of the data. However, choosing the best anomaly detector for a given dataset in a model-agnostic way is an important challenge which has hitherto largely been neglected. In this paper, we introduce the data-driven ARGOS metric, which has a sound theoretical foundation and is empirically shown to robustly select the most sensitive anomaly detection model given the data. Focusing on weakly supervised, classifier-based anomaly detection methods, we show that the ARGOS metric outperforms other model selection metrics previously used in the literature, in particular the binary cross-entropy loss. We explore several realistic applications, including hyperparameter tuning as well as architecture and feature selection. In all cases, we demonstrate that ARGOS is highly sensitive to the small amounts of signal present in anomaly detection analyses while at the same time being robust to background overfitting and background template mismodeling.
Förderung
- Deutsche Forschungsgemeinschaft
- U.S. Department of Energy
- RWTH Aachen University
Zitieren
APA
Hein, M., Kasieczka, G., Krämer, M., Moureaux, L., Mück, A., & Shih, D. (2026). How to pick the best anomaly detector?. Physical Review D, 114(1). https://doi.org/10.1103/9kcn-slvt
Vancouver
Hein M, Kasieczka G, Krämer M, Moureaux L, Mück A, Shih D. How to pick the best anomaly detector?. Physical Review D. 2026;114(1). doi:10.1103/9kcn-slvt
BibTeX
@article{Hein2026,
author = {Hein, Marie and Kasieczka, Gregor and Krämer, Michael and Moureaux, Louis and Mück, Alexander and Shih, David},
title = {How to pick the best anomaly detector?},
journal = {Physical Review D},
year = {2026},
volume = {114},
number = {1},
doi = {10.1103/9kcn-slvt}
}
EUVIMED