CERN Accelerating science

Talk
Title	Studies to mitigate difference between real data and simulation for jet tagging
Video	If you experience any problem watching the video, click the download button below Download Embed Mp4: Medium (1000 kbps) High (4000 kbps) More.. 800 kbps 800 kbps 800 kbps 1000 kbps 1000 kbps 2000 kbps 2000 kbps 2000 kbps 4000 kbps 4000 kbps Copy-paste this code into your page: <iframe width="640" height="360" frameborder="0" src="https://cds.cern.ch/video/2315380?showTitle=true" allowfullscreen></iframe> Copy-paste this code into your page to include both slides and lecture: <iframe src="https://mediastream.cern.ch/MediaArchive/Video/Public2/weblecture-player/index.html?year=2018&lecture=668017c23" width="1020px" height="600px" allowfullscreen scrolling="no" frameborder="0"></iframe>
Author(s)	Buchmuller, Oliver (speaker) (Imperial College (GB)) ; Martelli, Arabella (speaker) (Imperial College (GB)) ; Kieseler, Jan (speaker) (CERN) ; Verzetti, Mauro (speaker) (CERN) ; Stoye, Markus (speaker) (CERN)
Corporate author(s)	CERN. Geneva
Imprint	2018-04-10. - 0:20:37.
Series	(Machine Learning) (2nd IML Machine Learning Workshop)
Lecture note	on 2018-04-10T17:20:00
Subject category	Machine Learning
Abstract	The aim of the studies presented is to improve the performance of jet flavour tagging on real data while still exploiting a simulated dataset for the learning of the main classification task. In the presentation we explore “off the shelf” domain adaptation techniques as well as customised additions to them. The latter improves the calibration of the tagger, potentially leading to smaller systematic uncertainties. The studies are performed with simplified simulations for the case of b-jet tagging. The presentation will include first results as well as discuss pitfalls that we discovered during our research.
Copyright/License	© 2018-2024 CERN
Submitted by	paul.seyfert@cern.ch