English

Fast Point Cloud Generation with Diffusion Models in High Energy Physics

High Energy Physics - Phenomenology 2023-11-03 v2 High Energy Physics - Experiment

Abstract

Many particle physics datasets like those generated at colliders are described by continuous coordinates (in contrast to grid points like in an image), respect a number of symmetries (like permutation invariance), and have a stochastic dimensionality. For this reason, standard deep generative models that produce images or at least a fixed set of features are limiting. We introduce a new neural network simulation based on a diffusion model that addresses these limitations named Fast Point Cloud Diffusion (FPCD). We show that our approach can reproduce the complex properties of hadronic jets from proton-proton collisions with competitive precision to other recently proposed models. Additionally, we use a procedure called progressive distillation to accelerate the generation time of our method, which is typically a significant challenge for diffusion models despite their state-of-the-art precision.

Keywords

Cite

@article{arxiv.2304.01266,
  title  = {Fast Point Cloud Generation with Diffusion Models in High Energy Physics},
  author = {Vinicius Mikuni and Benjamin Nachman and Mariel Pettee},
  journal= {arXiv preprint arXiv:2304.01266},
  year   = {2023}
}

Comments

11 pages, 8 figures

R2 v1 2026-06-28T09:47:34.288Z