Machine Learning on sWeighted Data

TL;DR

This paper introduces a mathematically rigorous method to convert sPlot weights, which can be negative, into valid class probabilities, facilitating the application of machine learning techniques in high energy physics data analysis.

Contribution

The paper proposes a novel transformation of sPlot weights into probabilities, overcoming the challenge of negative weights for machine learning applications.

Findings

Enables neural network training with sPlot-derived data

Ensures weights are valid probabilities for ML models

Facilitates broader application of ML in high energy physics

Abstract

Data analysis in high energy physics has to deal with data samples produced from different sources. One of the most widely used ways to unfold their contributions is the sPlot technique. It uses the results of a maximum likelihood fit to assign weights to events. Some weights produced by sPlot are by design negative. Negative weights make it difficult to apply machine learning methods. The loss function becomes unbounded. This leads to divergent neural network training. In this paper we propose a mathematically rigorous way to transform the weights obtained by sPlot into class probabilities conditioned on observables, thus enabling to apply any machine learning algorithm out-of-the-box.