Non-Parametric Data-Driven Background Modelling using Conditional Probabilities

TL;DR

This paper introduces two innovative non-parametric, data-driven background modelling techniques for particle physics, addressing limitations of simulations and parametric models, especially with large datasets like those from CERN LHC.

Contribution

It presents two novel methods—ancestral sampling and GAN-based modelling—for flexible, accurate background estimation without relying on simulations or predefined functional forms.

Findings

Both methods effectively model backgrounds in benchmark analyses.

The GAN approach captures complex correlations in data.

The ancestral sampling method provides reliable background estimates.

Abstract

Background modelling is one of the main challenges in particle physics data analysis. Commonly employed strategies include the use of simulated events of the background processes, and the fitting of parametric background models to the observed data. However, reliable simulations are not always available or may be extremely costly to produce. As a result, in many cases, uncertainties associated with the accuracy or sample size of the simulation are the limiting factor in the analysis sensitivity. At the same time, parametric models are limited by the a priori unknown functional form and parameter values of the background distribution. These issues become ever more pressing when large datasets become available, as it is already the case at the CERN Large Hadron Collider, and when studying exclusive signatures involving hadronic backgrounds. Two novel and widely applicable non-parametric data-driven background modelling techniques are presented, which address these issues for a broad class of searches and measurements. The first, relying on ancestral sampling, uses data from a relaxed event selection to estimate a graph of conditional probability density functions of the variables used in the analysis, accounting for significant correlations. A background model is then generated by sampling events from this graph, before the full event selection is applied. In the second, a generative adversarial network is trained to estimate the joint probability density function of the variables used in the analysis. The training is performed on a relaxed event selection which excludes the signal region, and the network is conditioned on a blinding variable. Subsequently, the conditional probability density function is interpolated into the signal region to model the background. The application of each method on a benchmark analysis is presented in detail, and the performance is discussed.