Back To The Roots: Tree-Based Algorithms for Weakly Supervised Anomaly Detection

arXiv (Cornell University)

Abstract

Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (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. In this paper, we show that using boosted decision trees as classifiers in weakly supervised anomaly detection gives superior performance compared to deep neural networks. Boosted decision trees are well known for their effectiveness in tabular data analysis. Our results show that they not only offer significantly faster training and evaluation times, but they are also robust to a large number of noisy input features. By using advanced gradient boosted decision trees in combination with ensembling techniques and an extended set of features, we significantly improve the performance of weakly supervised methods for anomaly detection at the LHC. This advance is a crucial step towards a more model-agnostic search for new physics.

Authors 9

1. Thorben Finke Aachen Institut für Theoretische Teilchenphysik und Kosmologie

   RWTH Aachen University

   Affiliation as printed

   Institut für Theoretische Teilchenphysik und Kosmologie , RWTH Aachen , 52074 Aachen , Germany

2. Marie Hein Aachen Institut für Theoretische Teilchenphysik und Kosmologie

   RWTH Aachen University

   Affiliation as printed

   Institut für Theoretische Teilchenphysik und Kosmologie , RWTH Aachen , 52074 Aachen , Germany

3. Gregor Kasieczka

   Universität Hamburg

   Affiliation as printed

   Center for Data and Computing in Natural Sciences (CDCS) , 22607 Hamburg , Germany

   Institut für Experimentalphysik , Universität Hamburg , 22761 Hamburg , Germany

4. Michael Krämer
5. Alexander Mück
6. Parada Prangchaikul

   Universität Hamburg

   Affiliation as printed

   Institut für Experimentalphysik , Universität Hamburg , 22761 Hamburg , Germany

7. Tobias Quadfasel

   Universität Hamburg

   Affiliation as printed

   Institut für Experimentalphysik , Universität Hamburg , 22761 Hamburg , Germany

8. David Shih

   Rutgers, The State University of New Jersey · Environmental and Occupational Health Sciences Institute

   Affiliation as printed

   NHETC , Dept. of Physics and Astronomy , Rutgers University , Piscataway , NJ 08854 , USA

9. Manuel Sommerhalder

   Universität Hamburg

   Affiliation as printed

   Institut für Experimentalphysik , Universität Hamburg , 22761 Hamburg , Germany