Enhancing searches for resonances with machine learning and moment decomposition

TL;DR

This paper introduces a novel machine learning approach with a moment loss function that improves the detection of resonant signals in physics searches while maintaining accurate background estimation.

Contribution

It develops the Moment Decomposition (MoDe) method, a new tool that relaxes independence assumptions in classifiers without inducing background structures.

Findings

Enhanced sensitivity to new physics signals.

Maintained integrity of background estimation.

Flexible classifiers without localized background structures.

Abstract

A key challenge in searches for resonant new physics is that classifiers trained to enhance potential signals must not induce localized structures. Such structures could result in a false signal when the background is estimated from data using sideband methods. A variety of techniques have been developed to construct classifiers which are independent from the resonant feature (often a mass). Such strategies are sufficient to avoid localized structures, but are not necessary. We develop a new set of tools using a novel moment loss function (Moment Decomposition or MoDe) which relax the assumption of independence without creating structures in the background. By allowing classifiers to be more flexible, we enhance the sensitivity to new physics without compromising the fidelity of the background estimation.