Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 86: Searches/BSM V (Misc.)

T 86.5: Vortrag

Freitag, 4. April 2025, 10:00–10:15, ZHG010

Statistical analysis with anomaly detection — •Kristian Warnholz, Louis Moureaux, Gregor Kasieczka, and Manuel Sommerhalder — Universität Hamburg

Although extensive searches for new physics at the Large Hadron Collider have been conducted, no new particles beyond the Standard Model have been discovered. A key limitation may stem from the reliance on specific models to guide these searches, potentially overlooking more exotic phenomena. In response, recent years have seen the development of numerous machine learning-based, model-independent anomaly detection methods designed to uncover unexpected signals in the data. The first results using these methods have recently been published by the ATLAS and CMS Collaborations. We present a statistical analysis of the behavior of the p-values and exclusion limits derived using the anomaly detection process.

Keywords: anomaly detection; machine learning; statistics; dijet; model-agnostic