Speaker
Dr
Dominik Dannheim
(CERN)
Description
Probability-Density Estimation (PDE) is a multivariate discrimination technique based on sampling signal and background densities in a multi-dimensional phase space. The signal and background densities are defined by event samples (from data or monte carlo) and are evaluated using a binary search tree (range searching). This method is a powerful classification tool for problems with highly non-linearly correlated observables. In this paper, we present an innovative improvement of the PDE method that uses a self-adapting binning method to divide the multi-dimensional phase space in a finite number of hyper-rectangles (boxes). For a given number of boxes, the binning algorithm adjusts the size and position of the boxes inside the multidimensional phase space, minimizing the variance of the signal and background densities inside the boxes. The binned density information is stored in binary trees, allowing for a very fast and memory-efficient classification of events. The implementation of the binning algorithm (PDE-FOAM) is based on the monte-carlo integration package TFOAM included in the analysis package ROOT and has been developed within the framework of the Toolkit for Multivariate Data Analysis with ROOT (TMVA). We present performance results for representative examples (toy models) and discuss the dependence of the obtained results on the choice of parameters. The new PDE-FOAM is compared to the original PDE method based on range-searching.
Authors
Mr
Alexander Voigt
(CERN)
Dr
Dominik Dannheim
(CERN)
Dr
Peter Speckmayer
(Technische Universität Wien)
Dr
Tancredi Carli
(CERN)
