Automatizing the search for mass resonances using BumpNet

TL;DR

BumpNet is a machine learning approach that automates and enhances the search for mass resonances in collider data, improving sensitivity and efficiency over traditional methods.

Contribution

This work introduces BumpNet, a neural network-based tool that generalizes the Data-Directed Paradigm for resonance searches, enabling more effective detection of mass bumps in LHC data.

Findings

BumpNet accurately predicts significance distributions with minimal bias.

It demonstrates high sensitivity in detecting various mass bumps.

The method effectively manages the look-elsewhere effect.

Abstract

The search for resonant mass bumps in invariant-mass distributions remains a cornerstone strategy for uncovering Beyond the Standard Model (BSM) physics at the Large Hadron Collider (LHC). Traditional methods often rely on predefined functional forms and exhaustive computational and human resources, limiting the scope of tested final states and selections. This work presents BumpNet, a machine learning-based approach leveraging advanced neural network architectures to generalize and enhance the Data-Directed Paradigm (DDP) for resonance searches. Trained on a diverse dataset of smoothly-falling analytical functions and realistic simulated data, BumpNet efficiently predicts statistical significance distributions across varying histogram configurations, including those derived from LHC-like conditions. The network's performance is validated against idealized likelihood ratio-based tests, showing minimal bias and strong sensitivity in detecting mass bumps across a range of scenarios. Additionally, BumpNet's application to realistic BSM scenarios highlights its capability to identify subtle signals while managing the look-elsewhere effect. These results underscore BumpNet's potential to expand the reach of resonance searches, paving the way for more comprehensive explorations of LHC data in future analyses.