SciPost Submission Page

Deep-Learning Jets with Uncertainties and More

by Sven Bollweg, Manuel Haussmann, Gregor Kasieczka, Michel Luchmann, Tilman Plehn, Jennifer Thompson

Submission summary

As Contributors: Manuel Haussmann · Michel Luchmann
Arxiv Link: https://arxiv.org/abs/1904.10004v1
Date submitted: 2019-05-07
Submitted by: Luchmann, Michel
Submitted to: SciPost Physics
Domain(s): Theoretical
Subject area: High-Energy Physics - Phenomenology

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.

Current status:
Editor-in-charge assigned

Submission & Refereeing History

Submission 1904.10004v1 on 7 May 2019

Login to report or comment