Detecting New Physics as Novelty -- Complementarity Matters

TL;DR

This paper introduces a novel analysis scheme combining isolation-based and clustering-based novelty evaluators to improve detection of unexpected signals at colliders, demonstrated through simulated data and real LHC signals.

Contribution

It develops a new scheme leveraging complementarity between two novelty detection methods, enhancing collider anomaly detection capabilities.

Findings

Improved performance in simulated Gaussian samples.

Effective detection of narrow resonance in diphoton spectrum.

Encouraging sensitivities for LHC signals compared to existing searches.

Abstract

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.~\cite{Hajer:2018kqm}, between isolation-based 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 $t\bar{t}\gamma\gamma$ final state: $t\bar t h$, giving a narrow resonance in the diphoton mass spectrum, and gravity-mediated supersymmetry, which results in broad distributions at high transverse momentum. Compared to existing dedicated searches at the LHC, the sensitivities for both signals are found to be encouraging.