Converting sWeights to Probabilities with Density Ratios

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, negative sWeights produced by the sPlot technique can lead to issues in training 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 particular well suited to converting sWeights, with the benefit of fast prediction rates and adaptability to aspects of the experimental data such as data sample size and proportions of different event sources. We also show that a double density ratio approach where the initial drWeights are reweighted by an additional classifier gives substantially better results.