English

Deep-Learning Jets with Uncertainties and More

High Energy Physics - Phenomenology 2020-01-22 v2

Abstract

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We show how they capture statistical uncertainties from finite training samples, systematics related to the jet energy scale, and stability issues through pile-up. Altogether, Bayesian networks offer many new handles to understand and control deep learning at the LHC without introducing a visible prior effect and without compromising the network performance.

Keywords

Cite

@article{arxiv.1904.10004,
  title  = {Deep-Learning Jets with Uncertainties and More},
  author = {Sven Bollweg and Manuel Haussmann and Gregor Kasieczka and Michel Luchmann and Tilman Plehn and Jennifer Thompson},
  journal= {arXiv preprint arXiv:1904.10004},
  year   = {2020}
}

Comments

15 figures

R2 v1 2026-06-23T08:46:38.200Z