Probing Higgs exotic decay at the LHC with machine learning

TL;DR

This paper explores the use of deep neural networks, especially particle flow networks, to identify exotic Higgs decays into multiple b-quarks at the LHC, achieving high sensitivity projections for future collider runs.

Contribution

It demonstrates the effectiveness of particle flow networks in tagging complex Higgs decay signals and assesses their robustness across different event topologies.

Findings

PFN achieves the best performance among tested DNNs.

Projected sensitivities to Higgs decay branching ratios are 10 ext{,} 3 ext{,} and 1 ext{ extbackslash}% for 4, 6, and 8 b-quarks.

PFN remains effective even when trained on different event topologies.

Abstract

We study the tagging of Higgs exotic decay signals using different types of deep neural networks (DNNs), focusing on the $W^\pm h$ associated production channel followed by Higgs decaying into $n$ $b$-quarks with $n=4$, 6 and 8. All the Higgs decay products are collected into a fat-jet, to which we apply further selection using the DNNs. Three kinds of DNNs are considered, namely convolutional neural network (CNN), recursive neural network (RecNN) and particle flow network (PFN). The PFN can achieve the best performance because its structure allows enfolding more information in addition to the four-momentums of the jet constituents, such as particle ID and tracks parameters. Using the PFN as an example, we verify that it can serve as an efficient tagger even though it is trained on a different event topology with different $b$-multiplicity from the actual signal. The projected sensitivity to the branching ratio of Higgs decaying into $n$ $b$-quarks at the HL-LHC are 10\%, 3\% and 1\%, for $n=4$, 6 and 8, respectively.