In this paper, we train a Convolutional Neural Network to classify longitudinally and transversely polarized hadronic W± using the images of boosted W± jets as input. The images capture angular and energy information from the jet constituents that is faithful to properties of the original quark/anti-quark W± decay products without the need for invasive substructure cuts. We find that the difference between the polarizations is too subtle for the network to be used as an event-by-event tagger. However, given an ensemble of W± events with unknown polarization, the average network output from that ensemble can be used to extract the longitudinal fraction fL. We test the network on Standard Model pp→W±Z events and on pp→W±Z in the presence of dimension-6 operators that perturb the polarization composition.
@article{arxiv.2102.05124,
title = {A $W^\pm$ polarization analyzer from Deep Neural Networks},
author = {Taegyun Kim and Adam Martin},
journal= {arXiv preprint arXiv:2102.05124},
year = {2021}
}