Towards recognizing the light facet of the Higgs Boson

Abstract

The Higgs boson couplings to bottom and top quarks have been measured and agree well with the Standard Model predictions. Decays to lighter quarks and gluons, however, remain elusive. Observing these decays is essential to complete the picture of the Higgs boson interactions. In this work, we present the perspectives for the 14 TeV LHC to observe the Higgs boson decay to gluon jets assembling convolutional neural networks, trained to recognize abstract jet images constructed embodying particle flow information, and boosted decision trees with kinetic information from Higgs-strahlung $ZH\to {\ell }^{+}{\ell }^{-}+gg$ events. We show that this approach might be able to observe Higgs to gluon decays with a significance of around $2.4\sigma$ improving significantly previous prospects based on cut-and-count analysis. An upper bound of $BR(H\to gg)\le 1.74\times B{R}^{SM}(H\to gg)$ at 95\% confidence level after 3000 fb${}^{-1}$ of data is obtained using these machine learning techniques.

17 pages, 7 figures and 4 tables. Version accepted for publication in Machine Learning Science and Technology

References in corpus (19)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• mixup: Beyond Empirical Risk Minimization
• Machine learning and the physical sciences
• Mixed Precision Training
• A high-bias, low-variance introduction to Machine Learning for physicists
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• Automatic spin-entangled decays of heavy resonances in Monte Carlo simulations
• Don't Decay the Learning Rate, Increase the Batch Size
• Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
• Precision Measurements of Higgs Couplings: Implications for New Physics Scales
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Boosted Higgs Shapes
• Resonant Di-Higgs Production at Gravitational Wave Benchmarks: A Collider Study using Machine Learning
• Supervised deep learning in high energy phenomenology: a mini review
• Portraying Double Higgs at the Large Hadron Collider
• Topology classification with deep learning to improve real-time event selection at the LHC
• Higgs Boson Decay to Light Jets at the LHC
• CapsNets Continuing the Convolutional Quest
• Beyond $M_{t\bar{t}}$: learning to search for a broad $t\bar{t}$ resonance at the LHC

Cited by in corpus (7)

• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• The forgotten channels: charged Higgs boson decays to a $W^{\pm }$ and a non-SM-like Higgs boson
• Higgs boson tagging with the Lund jet plane
• Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks
• Higgs to charm quarks in vector boson fusion plus a photon
• Phenomenology at the Large Hadron Collider with Deep Learning: the case of vector-like quarks decaying to light jets
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects