EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets

Abstract

With the vast data-collecting capabilities of current and future high-energy collider experiments, there is an increasing demand for computationally efficient simulations. Generative machine learning models enable fast event generation, yet so far these approaches are largely constrained to fixed data structures and rigid detector geometries. In this paper, we introduce EPiC-GAN - equivariant point cloud generative adversarial network - which can produce point clouds of variable multiplicity. This flexible framework is based on deep sets and is well suited for simulating sprays of particles called jets. The generator and discriminator utilize multiple EPiC layers with an interpretable global latent vector. Crucially, the EPiC layers do not rely on pairwise information sharing between particles, which leads to a significant speed-up over graph- and transformer-based approaches with more complex relation diagrams. We demonstrate that EPiC-GAN scales well to large particle multiplicities and achieves high generation fidelity on benchmark jet generation tasks.

18 pages, 8 figures, 3 tables, code available at: https://github.com/uhh-pd-ml/EPiC-GAN

References in corpus (6)

• Score-Based Generative Modeling through Stochastic Differential Equations
• Brownian distance covariance
• Point-E: A System for Generating 3D Point Clouds from Complex Prompts
• Evaluating generative models in high energy physics
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• Conditional Set Generation with Transformers

Cited by in corpus (28)

• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• How to Understand Limitations of Generative Networks
• The MadNIS Reloaded
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• Precision-Machine Learning for the Matrix Element Method
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Normalizing Flows for High-Dimensional Detector Simulations
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Differentiable MadNIS-Lite
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• PIPPIN: Generating variable length full events from partons
• Flow Matching Beyond Kinematics: Generating Jets with Particle-ID and Trajectory Displacement Information
• Advancing Set-Conditional Set Generation: Diffusion Models for Fast Simulation of Reconstructed Particles
• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• ${\mathbb{Z}}_2\times {\mathbb{Z}}_2$ Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks
• Parnassus: An Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction
• Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming
• Ultra fast, event-by-event heavy-ion simulations for next generation experiments
• LHC Hadronic Jet Generation Using Convolutional Variational Autoencoders with Normalizing Flows
• Toward a foundation model for heavy-ion collision experiments based on point-cloud diffusion
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Equivariant neural networks for robust $\text{CP}$ observables
• BitHEP -- The Limits of Low-Precision ML in HEP
• Learnable cut flow for high energy physics