Aug 21 – 25, 2017
University of Washington, Seattle
US/Pacific timezone

Generative Adversarial Networks for Simulation

Aug 21, 2017, 4:30 PM
107 (Alder Hall)


Alder Hall

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


Luke Percival De Oliveira


We introduce the first use of deep neural network-based generative modeling for high energy physics (HEP). Our novel Generative Adversarial Network (GAN) architecture is able cope with the key challenges in HEP images, including sparsity and a large dynamic range. For example, our Location-Aware Generative Adversarial Network learns to produce realistic radiation patterns inside high energy jets - collimated sprays of particles resulting from quarks and gluons produced at high energy. The pixel intensities of the GAN-generated images faithfully span many orders of magnitude and reproduce the distributions of important low-dimensional physical properties (e.g. jet mass, n-subjettiness, etc.). We provide many visualizations of what the GAN has learned, to build additional confidence in the algorithm. Our results demonstrate that high-fidelity, fast simulation through GANs is a promising application of deep neural networks for solving one of the most important challenges facing HEP today.

Primary authors

Luke Percival De Oliveira Michela Paganini (Yale University (US)) Ben Nachman (Lawrence Berkeley National Lab. (US))

Presentation materials

Peer reviewing