Fast Point Cloud Generation with Diffusion Models in High Energy Physics

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.

arXiv comment11 pages, 8 figures

References in corpus (20)

• The anti-k_t jet clustering algorithm
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Jet-Images -- Deep Learning Edition
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Energy flow polynomials: A complete linear basis for jet substructure
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• AtlFast3: the next generation of fast simulation in ATLAS
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Machine Learning and LHC Event Generation
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• Score-based Generative Models for Calorimeter Shower Simulation
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• Deep Learning as a Parton Shower
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• GAN with an Auxiliary Regressor for the Fast Simulation of the Electromagnetic Calorimeter Response

Cited by in corpus (33)

• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• How to Understand Limitations of Generative Networks
• The MadNIS Reloaded
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• Diffusion Models as Stochastic Quantization in Lattice Field Theory
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Improving Generative Model-based Unfolding with Schrödinger Bridges
• High-dimensional and Permutation Invariant Anomaly Detection
• 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
• Calorimeter shower superresolution
• Differentiable MadNIS-Lite
• Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
• Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation
• End-to-end simulation of particle physics events with Flow Matching and generator Oversampling
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• Effectiveness of denoising diffusion probabilistic models for fast and high-fidelity whole-event simulation in high-energy heavy-ion experiments
• PIPPIN: Generating variable length full events from partons
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• Advancing Set-Conditional Set Generation: Diffusion Models for Fast Simulation of Reconstructed Particles
• Flow Matching Beyond Kinematics: Generating Jets with Particle-ID and Trajectory Displacement Information
• Describing Hadronization via Histories and Observables for Monte-Carlo Event Reweighting
• Parnassus: An Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction
• 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
• BitHEP -- The Limits of Low-Precision ML in HEP
• CaloHadronic: a diffusion model for the generation of hadronic showers
• Reconstructing Sparticle masses at the LHC using Generative Machine Learning
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
• Variational inference for pile-up removal at hadron colliders with diffusion models