MadMiner: Machine learning-based inference for particle physics
This tool aids precision measurements at the LHC by enabling more effective analysis of complex event data, though it is incremental as it builds on existing inference techniques.
The paper tackles the challenge of analyzing high-dimensional particle physics data for subtle kinematic signatures by introducing MadMiner, a Python module that streamlines machine learning-based inference techniques, and demonstrates in an example analysis of ttH production that these techniques substantially increase sensitivity to new physics.
Precision measurements at the LHC often require analyzing high-dimensional event data for subtle kinematic signatures, which is challenging for established analysis methods. Recently, a powerful family of multivariate inference techniques that leverage both matrix element information and machine learning has been developed. This approach neither requires the reduction of high-dimensional data to summary statistics nor any simplifications to the underlying physics or detector response. In this paper we introduce MadMiner, a Python module that streamlines the steps involved in this procedure. Wrapping around MadGraph5_aMC and Pythia 8, it supports almost any physics process and model. To aid phenomenological studies, the tool also wraps around Delphes 3, though it is extendable to a full Geant4-based detector simulation. We demonstrate the use of MadMiner in an example analysis of dimension-six operators in ttH production, finding that the new techniques substantially increase the sensitivity to new physics.