Digital Total - Computing & Data Science an der Universität Hamburg und in der Wissenschaftsmetropole Hamburg

Anomaly detection for discovery in particle physics

133

Nicht eingeplant

20m

Von-Melle-Park 4

Poster

Sprecher

Manuel Sommerhalder (Universität Hamburg, Institut für Experimentalphysik)

Beschreibung

In their quest to understand the fundamental law governing both the cosmos and interactions between particles, physicists are searching for small deviations from established theories in massive amounts of experimental data. Searches targeting specific signatures have yielded no positive results since the discovery of the Higgs boson, raising the question of whether the right signatures have been searched for. We present ML-based methods to address this problem by performing searches with minimal theory guidance.

Keywords

particle physics
anomaly detection
weak supervision
normalizing flow