Advancing Set-Conditional Set Generation: Diffusion Models for Fast Simulation of Reconstructed Particles

Abstract

The computational intensity of detector simulation and event reconstruction poses a significant difficulty for data analysis in collider experiments. This challenge inspires the continued development of machine learning techniques to serve as efficient surrogate models. We propose a fast emulation approach that combines simulation and reconstruction. In other words, a neural network generates a set of reconstructed objects conditioned on input particle sets. To make this possible, we advance set-conditional set generation with diffusion models. Using a realistic, generic, and public detector simulation and reconstruction package (COCOA), we show how diffusion models can accurately model the complex spectrum of reconstructed particles inside jets.

arXiv comment15 pages, 10 figures, 2 tables

References in corpus (18)

• A Brief Introduction to PYTHIA 8.1
• The ATLAS Simulation Infrastructure
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Machine Learning and LHC Event Generation
• AtlFast3: the next generation of fast simulation in ATLAS
• Score-based Generative Models for Calorimeter Shower Simulation
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• Reconstructing particles in jets using set transformer and hypergraph prediction networks
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• CaloShowerGAN, a Generative Adversarial Networks model for fast calorimeter shower simulation
• End-to-end simulation of particle physics events with Flow Matching and generator Oversampling
• Set-Conditional Set Generation for Particle Physics

Cited by in corpus (2)

• Parnassus: An Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction
• ParaFlow: fast calorimeter simulations parameterized in upstream material configurations