A Multivariate Training Technique with Event Reweighting

TL;DR

This paper introduces an event reweighting technique integrated into multivariate training algorithms like ANN and BDT, improving event pattern recognition in high-energy physics analysis at the LHC.

Contribution

It presents a novel event reweighting method for multivariate training, demonstrating its unbiased nature and performance benefits over conventional equal weighting.

Findings

Reweighting improves pattern recognition accuracy.

The method is unbiased and effective.

Applicable to LHC physics analysis.

Abstract

An event reweighting technique incorporated in multivariate training algorithm has been developed and tested using the Artificial Neural Networks (ANN) and Boosted Decision Trees (BDT). The event reweighting training are compared to that of the conventional equal event weighting based on the ANN and the BDT performance. The comparison is performed in the context of the physics analysis of the ATLAS experiment at the Large Hadron Collider (LHC), which will explore the fundamental nature of matter and the basic forces that shape our universe. We demonstrate that the event reweighting technique provides an unbiased method of multivariate training for event pattern recognition.