Year: 2025
Type: preprint
Abstract: Undetected anomalies in time series can trigger catastrophic failures in safety-critical systems, such as chemical plant explosions or power grid outages. Although many detection methods have been proposed, their performance remains unclear because current metrics capture only narrow aspects of the task and often yield misleading results. We address this issue by introducing verifiable properties that formalize essential requirements for evaluating time-series anomaly detection. These properties enable a theoretical framework that supports principled evaluations and reliable comparisons. Analyzing 37 widely used metrics, we show that most satisfy only a few properties, and none satisfy all, explaining persistent inconsistencies in prior results. To close this gap, we propose LARM, a flexible metric that provably satisfies all properties, and extend it to ALARM, an advanced variant meeting stricter requirements.
Source: arXiv (Cornell University)
Authors: Wagner, Dennis, Nair, Arjun, Franks, Billy Joe, Arweiler, Justus, Muraleedharan, Aparna, Jungjohann, Indra, Hartung, Fabian, Ahuja, Mayank C., Balinskyy, Andriy, Varshneya, Saurabh, Syed, Nabeel Hussain, Nagda, Mayank, Liznerski, Phillip, Reithermann, Steffen, Rudolph, Maja, Vollmer, Sebastian, Schulz, Ralf, Katz, Torsten, Mandt, Stephan, Bortz, Michael, Leitte, Heike, Neider, Daniel, Burger, Jakob, Jirasek, Fabian, Hasse, Hans, Fellenz, Sophie, Kloft, Marius
Institutions: Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau, University of Kaiserslautern, Technical University of Munich, BASF (Germany), University of Wisconsin–Madison, German Research Centre for Artificial Intelligence, University of California, Irvine, Fraunhofer Institute for Industrial Mathematics, TU Dortmund University
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Deutsche Forschungsgemeinschaft
Awards: G1595722819, SPP 2298: Theoretische Grundlagen von Deep Learning, G3334316370, G442688124, SPP 2331: Maschinelles Lernen in der Verfahrenstechnik. Wissen trifft auf Daten: Interpretierbarkeit, Extrapolation, Verlässlichkeit, Vertrauen, TRR 375: Multifunktionale Hochleistungskomponenten aus hybriden porösen Werkstoffen, FOR 5359: KIFOR: Deep Learning auf dünnbesetzten, chemischen Prozessdaten
OpenAlex ID: W4415964987
Cites:
Cited by:
Related to: