Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation

Abstract

Generation of simulated detector response to collision products is crucial to data analysis in particle physics, but computationally very expensive. One subdetector, the calorimeter, dominates the computational time due to the high granularity of its cells and complexity of the interactions. Generative models can provide more rapid sample production, but currently require significant effort to optimize performance for specific detector geometries, often requiring many models to describe the varying cell sizes and arrangements, without the ability to generalize to other geometries. We develop a $\text{geometry-aware}$ autoregressive model, which learns how the calorimeter response varies with geometry, and is capable of generating simulated responses to unseen geometries without additional training. The geometry-aware model outperforms a baseline unaware model by over $50\%$ in several metrics such as the Wasserstein distance between the generated and the true distributions of key quantities which summarize the simulated response. A single geometry-aware model could replace the hundreds of generative models currently designed for calorimeter simulation by physicists analyzing data collected at the Large Hadron Collider. This proof-of-concept study motivates the design of a foundational model that will be a crucial tool for the study of future detectors, dramatically reducing the large upfront investment usually needed to develop generative calorimeter models.

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• MADE: Masked Autoencoder for Distribution Estimation
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• 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
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Evaluating generative models in high energy physics
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• Resolving Extreme Jet Substructure
• Generative Adversarial Networks for LHCb Fast Simulation

Cited by in corpus (6)

• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• Anomaly detection with flow-based fast calorimeter simulators
• Leveraging Staggered Tessellation for Enhanced Spatial Resolution in High-Granularity Calorimeters
• ParaFlow: fast calorimeter simulations parameterized in upstream material configurations