Frequentist Uncertainties on Neural Density Ratios with wifi Ensembles

TL;DR

This paper introduces wifi ensembles, a novel method for obtaining frequentist uncertainties on neural density ratios, enabling simulation-based inference in high-energy physics without bootstrapping.

Contribution

The paper presents wifi ensembles as a new framework for uncertainty quantification in neural density ratio estimation, especially for likelihood ratios conditioned on parameters.

Findings

Successfully estimated likelihood ratios between quark and gluon jets.

Uncertainties from wifi ensembles satisfy coverage properties.

Applied method to quantum chromodynamics at LHC.

Abstract

We introduce wifi ensembles as a novel framework to obtain asymptotic frequentist uncertainties on density ratios, with a particular focus on neural ratio estimation in the context of high-energy physics. When the density ratio of interest is a likelihood ratio conditioned on parameters, wifi ensembles can be used to perform simulation-based inference on those parameters. After training the basis functions f_i(x), uncertainties on the weights w_i can be straightforwardly propagated to the estimated parameters without requiring extraneous bootstraps. To demonstrate this approach, we present an application in quantum chromodynamics at the Large Hadron Collider, using wifi ensembles to estimate the likelihood ratio between generated quark and gluon jets. We use this learned likelihood ratio to estimate the quark fraction in a synthetic mixed quark/gluon sample, showing that the resultant uncertainties empirically satisfy the desired coverage properties.