Speaker
Marie Hein
(RWTH Aachen University)
Description
Weakly supervised methods have emerged as a powerful tool for model agnostic anomaly detection at the LHC. While these methods have shown remarkable performance on specific signatures such as di-jet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. We show that neural networks struggle with noisy input features and that this issue can be solved by using boosted decision trees. Overall, boosted decision trees have a superior performance in the weakly supervised setting than neural networks. Additionally, we significantly improve the performance by using an extended set of features.
Primary authors
Thorben Finke
(RWTH Aachen University)
Marie Hein
(RWTH Aachen University)
Gregor Kasieczka
(Universität Hamburg)
Michael Krämer
(RWTH Aachen University)
Alexander Mück
(RWTH Aachen University)
Parada Prangchaikul
(Universität Hamburg)
Tobias Quadfasel
(Universität Hamburg)
David Shih
(Rutgers University)
Manuel Sommerhalder
(Universität Hamburg)
