Sorry, I don't understand your search. ×
Back to Search Start Over

Per-Object Systematics using Deep-Learned Calibration

Authors :
Kasieczka, Gregor
Luchmann, Michel
Otterpohl, Florian
Plehn, Tilman
Source :
SciPost Phys. 9, 089 (2020)
Publication Year :
2020

Abstract

We show how to treat systematic uncertainties using Bayesian deep networks for regression. First, we analyze how these networks separately trace statistical and systematic uncertainties on the momenta of boosted top quarks forming fat jets. Next, we propose a novel calibration procedure by training on labels and their error bars. Again, the network cleanly separates the different uncertainties. As a technical side effect, we show how Bayesian networks can be extended to describe non-Gaussian features.

Details

Database :
arXiv
Journal :
SciPost Phys. 9, 089 (2020)
Publication Type :
Report
Accession number :
edsarx.2003.11099
Document Type :
Working Paper
Full Text :
https://doi.org/10.21468/SciPostPhys.9.6.089