Converting sWeights to Probabilities with Density Ratios

TL;DR

This paper introduces a method to convert negative sWeights into positive event probabilities using density ratio estimation, improving the reliability of background subtraction in experimental physics data analysis.

Contribution

It presents a novel approach to transform sPlot sWeights into event probabilities with density ratio estimation, enhancing data analysis accuracy in physics experiments.

Findings

drWeights are consistent with direct sWeights use

Decision trees efficiently convert sWeights with fast predictions

Reweighted density ratio products improve results

Abstract

The use of machine learning approaches continues to have many benefits in experimental nuclear and particle physics. One common issue is generating training data which is sufficiently realistic to give reliable results. Here we advocate using real experimental data as the source of training data and demonstrate how one might subtract background contributions through the use of probabilistic weights which can be readily applied to training data. The sPlot formalism is a common tool used to isolate distributions from different sources. However, the negative sWeights produced by the sPlot technique can cause training problems and poor predictive power. This article demonstrates how density ratio estimation can be applied to convert sWeights to event probabilities, which we call drWeights. The drWeights can then be applied to produce the distributions of interest and are consistent with direct use of the sWeights. This article will also show how decision trees are particularly well suited to convert sWeights, with the benefit of fast prediction rates and adaptability to aspects of experimental data such as the data sample size and proportions of different event sources. We also show that a density ratio product approach in which the initial drWeights are reweighted by an additional converter gives substantially better results.