Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning

Abstract

The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with this hypothesis, current analysis techniques lack the statistical power to cross the traditional 5$\sigma$ significance barrier without more data. \emph{Deep learning} techniques have the potential to increase the statistical power of this analysis by \emph{automatically} learning complex, high-level data representations. In this work, deep neural networks are used to detect the decay of the Higgs to a pair of tau leptons. A Bayesian optimization algorithm is used to tune the network architecture and training algorithm hyperparameters, resulting in a deep network of eight non-linear processing layers that improves upon the performance of shallow classifiers even without the use of features specifically engineered by physicists for this application. The improvement in discovery significance is equivalent to an increase in the accumulated dataset of 25\%.

For submission to PRL

References in corpus (2)

• PYTHIA 6.4 Physics and Manual
• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (11)

• Learning Activation Functions to Improve Deep Neural Networks
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Jet-Parton Assignment in ttH Events using Deep Learning
• Precision SMEFT bounds from the VBF Higgs at high transverse momentum
• Classification and Recovery of Radio Signals from Cosmic Ray Induced Air Showers with Deep Learning
• Artificial Neural Networks for cosmic gamma-ray propagation in the Universe
• A universal neural network for learning phases and criticalities
• Scientists in silico?
• Energy Flow in Particle Collisions