Bayesian Neural Networks for Fast SUSY Predictions
This work addresses the challenge of testing new physics theories in particle physics by providing fast and accurate predictions, though it is incremental as it applies an existing machine learning method to a specific domain problem.
The paper tackled the problem of efficiently predicting outcomes from the high-dimensional parameter space of the phenomenological Minimal Supersymmetric Standard Model (pMSSM) using Bayesian neural networks, achieving average percent errors of 3.34% or less for cross sections, Higgs boson mass, and theoretical viability, with significantly faster computation than traditional methods.
One of the goals of current particle physics research is to obtain evidence for new physics, that is, physics beyond the Standard Model (BSM), at accelerators such as the Large Hadron Collider (LHC) at CERN. The searches for new physics are often guided by BSM theories that depend on many unknown parameters, which, in some cases, makes testing their predictions difficult. In this paper, machine learning is used to model the mapping from the parameter space of the phenomenological Minimal Supersymmetric Standard Model (pMSSM), a BSM theory with 19 free parameters, to some of its predictions. Bayesian neural networks are used to predict cross sections for arbitrary pMSSM parameter points, the mass of the associated lightest neutral Higgs boson, and the theoretical viability of the parameter points. All three quantities are modeled with average percent errors of 3.34% or less and in a time significantly shorter than is possible with the supersymmetry codes from which the results are derived. These results are a further demonstration of the potential for machine learning to model accurately the mapping from the high dimensional spaces of BSM theories to their predictions.