Enhanced Higgs to $τ^+τ^-$ Searches with Deep Learning
This work addresses the challenge of enhancing statistical power in particle physics searches for Higgs boson decays, representing an incremental improvement in analysis techniques for high-energy physics experiments.
The paper tackled the problem of detecting Higgs boson decays to tau leptons at the LHC, where current methods lack statistical power to reach 5σ significance without more data, and used deep neural networks to improve discovery significance by an amount equivalent to a 25% increase in dataset size.
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$σ$ 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\%.