Reconstruction of Missing Resonances Combining Nearest Neighbors Regressors and Neural Network Classifiers

TL;DR

This paper presents a method combining k-nearest neighbors regressors and neural network classifiers to reconstruct missing resonance information in particle physics, improving signal-background separation and resonance peak identification.

Contribution

It introduces a novel approach using kNN regressors with neural networks to recover resonance distributions from detector data, aiding post-discovery analysis.

Findings

Accurately reconstructs the fully leptonic WW mass distribution.

Enhances classifier performance for signal-background separation.

Improves statistical significance of Higgs boson detection.

Abstract

Neutrinos, dark matter, and long-lived neutral particles traverse the particle detectors unnoticed, carrying away information about their parent particles and interaction sources needed to reconstruct key variables like resonance peaks in invariant mass distributions. In this work, we show that a $k$-nearest neighbors regressor algorithm combined with deep neural network classifiers, a $k$NN, is able to accurately recover binned distributions of the fully leptonic $WW$ mass of a new heavy Higgs boson and its Standard Model backgrounds from the observable detector level information at disposal. The output of the regressor can be used to train even stronger classifiers to separate signals and backgrounds in the fully leptonic case and guarantee the selection of on-mass-shell Higgs bosons with enhanced statistical significance. The method assumes previous knowledge of the event classes and model parameters, thus suitable for post-discovery studies.