Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN

TL;DR

This paper introduces a novel application of diffusion models for simulating particle collisions at CERN, demonstrating higher fidelity and faster generation times than existing methods like VAEs and GANs.

Contribution

First application of diffusion models for high-energy physics simulation, achieving superior fidelity and efficiency in modeling particle collision data at CERN.

Findings

Diffusion models outperform VAEs and GANs in simulation fidelity.

Latent diffusion models offer rapid generation times.

Significant potential for real-time physics simulations.

Abstract

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.