Speakers
Description
In a physics data analysis, "fake" or non-prompt backgrounds refer to events that would not typically satisfy the selection criteria for a given signal region, but are nonetheless accepted due to misreconstructed particles. This can occur, for example, when particles from secondary decays are incorrectly identified as originating from the hard scatter interaction point (resulting in non-prompt leptons), or when other physics objects, such as hadronic jets, are mistakenly reconstructed as leptons (resulting in fake leptons). These fake particles are taken into account by calculating a scale factor (a fake factor) and applying it as an event weight obtained by a data-driven technique. Traditionally, fake factors have been estimated by histogramming and computing the ratio of two distributions, typically as functions of a few relevant physics variables such as $p_{\mathrm{T}}$, $\eta$, and MET. In this work, we present a novel approach based on density ratio estimation using a transformer neural network trained directly on event data in a high-dimensional feature space. This enables the computation of a continuous, unbinned fake factor on a per-event basis, offering a more flexible, precise and higher-dimensional alternative to the conventional method.
References
- Systematic evaluation of generative machine learning capability to simulate distributions of observables at the large hadron collider: https://link.springer.com/article/10.1140/epjc/s10052-024-13284-6
- Normalizing Flows for Physics Data Analyses, presented at Conference on Computing in High Energy and Nuclear Physics 2024: https://indico.cern.ch/event/1338689/contributions/6016108/
Significance
The method presented is a novel approach on calculating any scale factor (not just a fake factor) using machine learning. The final result of the method is a function (neural network) that takes in an event and calculates an appropriate scale factor in high feature dimensional spaces.
| Experiment context, if any | The method can be used by any HEP analysis and is not experiment specific. |
|---|
