Speaker
Paula Schuchard
Description
Classical searches for BSM physics at the LHC suffer from two shortcomings: they tend to be dependent on one particular BSM model and they rarely include the information of the full, high-dimensional physical phase space. Recently, machine learning has been successfully applied to enhance resonant searches at LHC experiments addressing both shortcomings. In this talk we explore options to analogously develop non-resonant, model-agnostic searches with generative machine learning.
