Machine learning techniques are increasingly being applied toward data analyses at the Large Hadron Collider, especially with applications for discrimination of jets with different originating particles. In this talk, I will review machine learning at the LHC and discuss a systematic and constructive approach to extracting the information necessary for discrimination. By measuring observables on jets that completely and minimally span N-body phase space, we are able to reduce the problem in a controlled and theoretically well-defined way. For the application of discrimination of QCD jets versus boosted hadronically-decaying Z bosons, we show that discrimination power is saturated by only considering observables that are sensitive to 4-body (8 dimensional) phase space.
(Massachusetts Institute of Technology),