abstract: A key research question at the Large Hadron Collider is the test of models of new physics. Testing if a particular parameter set of such a model is excluded by LHC data is a challenge: it requires time consuming generation of scattering events, simulation of the detector response, event reconstruction, cross section calculations and analysis code to test against several hundred signal regions defined by the ATLAS and CMS experiments. Tackling this challenge with the usual pipeline of software can take up to an hour (or even hours) for a single model point.
In my talk, i will present machine learning as a new approach to this challenge. I will show a first example applied to the 19-dimensional phenomenological MSSM (pMSSM), a generic phenomenological supersymmetry model. We will see that it is able to predict the ATLAS exclusion within a fraction of a second with an accuracy of at least 93% directly from the parameters of the model point.
The code, called SUSY-AI, and its future BSM derivatives will help to solve the problem of recasting LHC results for any model of new physics. SUSY-AI can already be downloaded from http://susyai.hepforge.org/. An on-line interface to the program for quick testing purposes can be found at http://www.susy-ai.org/.