10-15 March 2019
Steinmatte conference center
Europe/Zurich timezone

Adversarial Neural Network-based data-simulation corrections for jet-tagging at CMS

13 Mar 2019, 16:10
Steinmatte Room A

Steinmatte Room A

Oral Track 2: Data Analysis - Algorithms and Tools Track 2: Data Analysis - Algorithms and Tools


Benjamin Fischer (Rheinisch Westfaelische Tech. Hoch. (DE))


Variable-dependent scale factors are commonly used in HEP to improve shape agreement of data and simulation. The choice of the underlying model is of great importance, but often requires a lot of manual tuning e.g. of bin sizes or fitted functions. This can be alleviated through the use of neural networks and their inherent powerful data modeling capabilities.
We present a novel and generalized method for producing scale factors using an adversarial neural network. This method is investigated in the context of the bottom-quark jet-tagging algorithms within the CMS experiment. The primary network uses the jet variables as inputs to derive the scale factor for a single jet. It is trained through the use of a second network, the adversary, which aims to differentiate between the data and rescaled simulation.

Primary authors

Benjamin Fischer (Rheinisch Westfaelische Tech. Hoch. (DE)) David Josef Schmidt (Rheinisch Westfaelische Tech. Hoch. (DE)) Dennis Noll (Rheinisch Westfaelische Tech. Hoch. (DE)) Marcel Rieger (Rheinisch-Westfaelische Tech. Hoch. (DE)) Martin Erdmann (Rheinisch-Westfaelische Tech. Hoch. (DE)) Yannik Alexander Rath (RWTH Aachen University (DE))

Presentation materials

Peer reviewing