Abstract
Investigation of physical well-motivated parameter space in the theories of
Beyond the Standard Model (BSM) plays an important role in new physics
discoveries. However, a large-scale scan of high dimensional (HD) parameter
space under vast experimental constraints is typically a time-consuming and
expensive task. In this Letter, we propose a novel self-learning scan strategy,
named Machine Learning Scan (MLS), to achieve a fast and reliable analysis of
HD parameter space by using machine learning models to evaluate the quality of
random parameter sets. As a proof-of-concept, we apply MLS to find the light
Higgs and light neutralino dark matter scenario in pMSSM and find that such a
method can significantly reduce the computational cost (two orders faster than
the standard random scan) and ensure a full coverage of survived regions.
Users
Please
log in to take part in the discussion (add own reviews or comments).