EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion

Abstract

Jets at the LHC, typically consisting of a large number of highly correlated particles, are a fascinating laboratory for deep generative modeling. In this paper, we present two novel methods that generate LHC jets as point clouds efficiently and accurately. We introduce \epcjedi, which combines score-matching diffusion models with the Equivariant Point Cloud (EPiC) architecture based on the deep sets framework. This model offers a much faster alternative to previous transformer-based diffusion models without reducing the quality of the generated jets. In addition, we introduce \epcfm, the first permutation equivariant continuous normalizing flow (CNF) for particle cloud generation. This model is trained with {\it flow-matching}, a scalable and easy-to-train objective based on optimal transport that directly regresses the vector fields connecting the Gaussian noise prior to the data distribution. Our experiments demonstrate that \epcjedi and \epcfm both achieve state-of-the-art performance on the top-quark JetNet datasets whilst maintaining fast generation speed. Most notably, we find that the \epcfm model consistently outperforms all the other generative models considered here across every metric. Finally, we also introduce two new particle cloud performance metrics: the first based on the Kullback-Leibler divergence between feature distributions, the second is the negative log-posterior of a multi-model ParticleNet classifier.

arXiv comment21 pages, 8 figures

Cited by in corpus (12)

• The MadNIS Reloaded
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• Precision-Machine Learning for the Matrix Element Method
• Normalizing Flows for High-Dimensional Detector Simulations
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Differentiable MadNIS-Lite
• Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• Describing Hadronization via Histories and Observables for Monte-Carlo Event Reweighting
• Generative Unfolding with Distribution Mapping
• BitHEP -- The Limits of Low-Precision ML in HEP
• Choose Your Diffusion: Efficient and flexible ways to accelerate the diffusion model in fast high energy physics simulation