Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
arXiv:2012.00173
Abstract
We develop a graph generative adversarial network to generate sparse data sets like those produced at the CERN Large Hadron Collider (LHC). We demonstrate this approach by training on and generating sparse representations of MNIST handwritten digit images and jets of particles in proton-proton collisions like those at the LHC. We find the model successfully generates sparse MNIST digits and particle jet data. We quantify agreement between real and generated data with a graph-based Fréchet Inception distance, and the particle and jet feature-level 1-Wasserstein distance for the MNIST and jet datasets respectively.
9 pages, 4 figures, 4 tables, To appear in Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020)
References in corpus (15)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Neural Message Passing for Quantum Chemistry
- Training Generative Adversarial Networks with Limited Data
- CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
- Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
- How to GAN LHC Events
- Least Squares Generative Adversarial Networks
- Image Augmentations for GAN Training
- Fast and accurate simulation of particle detectors using generative adversarial networks
- Lund jet images from generative and cycle-consistent adversarial networks
- LHC analysis-specific datasets with Generative Adversarial Networks
- SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
- Implicit competitive regularization in GANs
- The CMS HGCAL detector for HL-LHC upgrade