Detecting new physics as novelty - Complementarity matters

Novelty detection is a task of machine learning that aims at detecting novel events without a prior knowledge. In particular, its techniques can be applied to detect unexpected signals from new phenomena at colliders. In this paper, we develop an analysis scheme that exploits the complementarity, originally studied in ref. [1], between isolationbased and clustering-based novelty evaluators. This approach can significantly improve the performance and overall applicability of novelty detection at colliders, which we demonstrate using a variety of two dimensional Gaussian samples mimicking collider events. As a further proof of principle, we subsequently apply this scheme to the detection of two significantly different signals at the LHC featuring a t (t) over bar gamma gamma final state: t (t) over bar th, giving a narrow resonance in the diphoton mass spectrum, and gravity-mediated supersymmetry, resulting in broad distributions at high transverse momentum. Compared to existing dedicated searches at the LHC, the sensitivities for detecting both signals are found to be encouraging.

Automated summary

This paper introduces an analysis scheme for novelty detection, aiming to improve performance and applicability by utilizing the complementarity between isolation-based and clustering-based novelty evaluators. The scheme is validated using Gaussian samples mimicking collider events, and successfully applied to the detection of two different signals at LHC.