Timezone: »

Particle Cloud Generation with Message Passing Generative Adversarial Networks
Raghav Kansal · Javier Duarte · Hao Su · Breno Orzari · Thiago Tomei · Maurizio Pierini · Mary Touranakou · jean-roch vlimant · Dimitrios Gunopulos

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @ None #None

In high energy physics (HEP), jets are collections of correlated particles produced ubiquitously in particle collisions such as those at the CERN Large Hadron Collider (LHC). Machine learning (ML)-based generative models, such as generative adversarial networks (GANs), have the potential to significantly accelerate LHC jet simulations. However, despite jets having a natural representation as a set of particles in momentum-space, a.k.a. a particle cloud, there exist no generative models applied to such a dataset. In this work, we introduce a new particle cloud dataset (JetNet), and apply to it existing point cloud GANs. Results are evaluated using (1) 1-Wasserstein distances between high- and low-level feature distributions, (2) a newly developed Fréchet ParticleNet Distance, and (3) the coverage and (4) minimum matching distance metrics. Existing GANs are found to be inadequate for physics applications, hence we develop a new message passing GAN (MPGAN), which outperforms existing point cloud GANs on virtually every metric and shows promise for use in HEP. We propose JetNet as a novel point-cloud-style dataset for the ML community to experiment with, and set MPGAN as a benchmark to improve upon for future generative models. Additionally, to facilitate research and improve accessibility and reproducibility in this area, we release the open-source JetNet Python package with interfaces for particle cloud datasets, implementations for evaluation and loss metrics, and more tools for ML in HEP development.

Author Information

Raghav Kansal (UC San Diego)
Javier Duarte (University of California San Diego)
Hao Su (Stanford)
Breno Orzari (Instituto de Física Teórica - UNESP)
Thiago Tomei (Universidade Estadual Paulista)
Maurizio Pierini (CERN)
Mary Touranakou (CERN)
jean-roch vlimant (California Institute of Technology)
Dimitrios Gunopulos

More from the Same Authors