Classify the Higgs decays with the PFN and ParticleNet at electron-positron colliders

TL;DR

This paper explores using advanced neural network techniques, Particle Flow Network and ParticleNet, to classify Higgs boson decays at electron-positron colliders, aiming for a comprehensive, model-independent analysis of decay modes.

Contribution

It introduces the application of PFN and ParticleNet for multi-category Higgs decay classification in a simulated collider environment, enabling an end-to-end analysis approach.

Findings

Feasibility demonstrated through Monte Carlo simulations.

Promising classification performance for Higgs decay modes.

Potential for simultaneous measurement of all Higgs branching fractions.

Abstract

Various Higgs factories are proposed to study the Higgs boson precisely and systematically in a model-independent way. In this study, the Particle Flow Network and ParticleNet techniques are used to classify the Higgs decays into multi-categories and the ultimate goal is to realize an "end-to-end" analysis. A Monte Carlo simulation study is performed to demonstrate the feasibility, and the performance looks rather promising. This result could be the basis of a "one-shop" analysis to measure all the branching fractions of the Higgs decays simultaneously.