Decision tree-based estimation of the overlap of two probability distributions

Abstract

A new nonparametric approach, based on a decision tree algorithm, is proposed to calculate the overlap between two probability distributions. The devised framework is described analytically and numerically. The convergence of the estimated overlap to the true value is proved along with some experimental results.

arXiv comment23 pages, 7 figures. Accepted for publication in Journal of Mathematical Sciences, the University of Tokyo