QCD-jets at the LHC are described by simple physics principles. We show how super-resolution generative networks can learn the underlying structures and use them to improve the resolution of jet images. We test this approach on massless QCD-jets and on fat top-jets and find that the network reproduces their main features even without training on pure samples. In addition, we show how a slim network architecture can be constructed once we have control of the full network performance.
@article{arxiv.2012.11944,
title = {How to GAN Higher Jet Resolution},
author = {Pierre Baldi and Lukas Blecher and Anja Butter and Julian Collado and Jessica N. Howard and Fabian Keilbach and Tilman Plehn and Gregor Kasieczka and Daniel Whiteson},
journal= {arXiv preprint arXiv:2012.11944},
year = {2021}
}
Comments
25 pages, 11 figures; implemented SciPost reviewer comments, clarified definitions and expanded discussion in high-level observable benchmarking subsection (section 3.3 and Fig. 7)