Münster 2017 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 21: Experimentelle Methoden 1 (Computing, Machine Learning, Statistik)

T 21.6: Vortrag

Montag, 27. März 2017, 18:00–18:15, JUR 253

Multivariate Regression on the Example of Missing Transverse Energy Estimation — •Nicola Zäh, Raphael Friese, Günther Quast, and Roger Wolf — Institut f\"ur Experimentelle Kernphysik, Karlsruhe, Germany

Boosted decision trees are commonly used for classification in the field of particle physics. A similar technique, gradient boosted regression trees, can be applied to regression tasks. The resolution of missing transverse energy is an important quantity in particle physics and can be improved by using multivariate analysing techniques.

In this talk the performance of gradient boosted regression trees will be compared with other methods to calculate this quantity.