Speaker
Description
We consider the application of machine learning techniques to searches at the Large Hadron Collider (LHC) for pair-produced lepton partners which decay to leptons and invisible particles. This scenario can arise in the Minimal Supersymmetric Standard Model (MSSM), but can be realized in many other models. We focus on the case of intermediate bino-slepton mass splitting (~ 30 GeV), for which, due to large electroweak backgrounds, the LHC has made little improvement over LEP. As a benchmark, we find that the use of machine learning techniques can push the LHC well past discovery sensitivity for a right-handed muon partner with mass of ~110 GeV, for an integrated luminosity of 300 fb^{-1}, with a signal-to-background ratio of ~0.5. We identify several machine learning techniques which can be useful in other LHC searches involving large and complex backgrounds.
