Efficient search for new physics using Active Learning in the ATLAS Experiment

Searches for new physics at the LHC set exclusion limits in multi-dimensional parameter spaces of various theories. Typically, these are presented as 1- or 2-dimensional parameter scans; however, the relevant theory’s parameter space is usually of a higher dimension. As a result only a subspace is covered, which is due to the exponential computing requirements of simulations for scattering processes of interest. An Active Learning approach using a Gaussian Process is presented to address this limitation. Compared to the usual grid scan, this iterative procedure reduces the number of points in parameter space for which exclusion limits need to be determined. The Active Learning procedure is applied to a dark matter search performed by the ATLAS experiment, extending its interpretation from a 2 to a 4-dimensional parameter space while keeping the computational effort at a low level.