Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kita, Mikołaj, Dubiński, Jan, Rokita, Przemysław, Deja, Kamil
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916275119194112
author Kita, Mikołaj
Dubiński, Jan
Rokita, Przemysław
Deja, Kamil
author_facet Kita, Mikołaj
Dubiński, Jan
Rokita, Przemysław
Deja, Kamil
contents In High Energy Physics simulations play a crucial role in unraveling the complexities of particle collision experiments within CERN's Large Hadron Collider. Machine learning simulation methods have garnered attention as promising alternatives to traditional approaches. While existing methods mainly employ Variational Autoencoders (VAEs) or Generative Adversarial Networks (GANs), recent advancements highlight the efficacy of diffusion models as state-of-the-art generative machine learning methods. We present the first simulation for Zero Degree Calorimeter (ZDC) at the ALICE experiment based on diffusion models, achieving the highest fidelity compared to existing baselines. We perform an analysis of trade-offs between generation times and the simulation quality. The results indicate a significant potential of latent diffusion model due to its rapid generation time.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03233
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN
Kita, Mikołaj
Dubiński, Jan
Rokita, Przemysław
Deja, Kamil
Data Analysis, Statistics and Probability
Computer Vision and Pattern Recognition
High Energy Physics - Experiment
In High Energy Physics simulations play a crucial role in unraveling the complexities of particle collision experiments within CERN's Large Hadron Collider. Machine learning simulation methods have garnered attention as promising alternatives to traditional approaches. While existing methods mainly employ Variational Autoencoders (VAEs) or Generative Adversarial Networks (GANs), recent advancements highlight the efficacy of diffusion models as state-of-the-art generative machine learning methods. We present the first simulation for Zero Degree Calorimeter (ZDC) at the ALICE experiment based on diffusion models, achieving the highest fidelity compared to existing baselines. We perform an analysis of trade-offs between generation times and the simulation quality. The results indicate a significant potential of latent diffusion model due to its rapid generation time.
title Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN
topic Data Analysis, Statistics and Probability
Computer Vision and Pattern Recognition
High Energy Physics - Experiment
url https://arxiv.org/abs/2406.03233