Generative Adversarial Networks for fast simulation. (April 2020)

• Record Type: Journal Article
• Authors: Carminati, Federico; Khattak, Gulrukh; Loncar, Vladimir; Nguyen, Thong Q; Pierini, Maurizio; Brito Da Rocha, Ricardo; Samaras-Tsakiris, Konstantinos; Vallecorsa, Sofia; Vlimant, Jean-Roch
• Is Part Of: Journal of physics. Volume 1525(2020)
• Publication Date: 2020-04
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1525/1/012064
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Deep Learning techniques are being studied for different applications by the HEP community: in this talk, we discuss the case of detector simulation. The need for simulated events, expected in the future for LHC experiments and their High Luminosity upgrades, is increasing dramatically and requires new fast simulation solutions. Here we present updated results on the development of 3DGAN, one of the first examples using three-dimensional convolutional Generative Adversarial Networks to simulate high granularity electromagnetic calorimeters. In particular, we report on two main aspects: results on the simulation of a more general, realistic physics use case and on data parallel strategies to distribute the training process across multiple nodes on public cloud resources.