Exploration of Parameter Spaces Assisted by Machine Learning

Abstract

We demonstrate two sampling procedures assisted by machine learning models via regression and classification. The objective is the construction of routines that can be employed for different types of analysis, from finding bounds on the parameter space to accumulating samples in areas of interest. Moreover, for classification, we introduce a boosting technique to improve cases where the initial convergence is slow. The type of results that can be obtained is better explained with the help of a few examples from sampling simple toy models to exploring the parameter space of the two Higgs doublet model. The code used for this paper and instructions are publicly available on the web 1 .