Fast multi-geometry calorimeter simulation with conditional self-attention variational autoencoders

TL;DR

This paper introduces a geometry-aware variational autoencoder that efficiently simulates detector responses in particle physics, significantly reducing computational costs and outperforming existing models by over 70%.

Contribution

It presents a novel, geometry-conditioned autoencoder that leverages detector regularity, simplifying model specification and enhancing simulation accuracy.

Findings

Outperforms state-of-the-art models by over 70% on key metrics

Requires only cell size definitions for regular detector segments

Reduces computational complexity of detector response simulation

Abstract

The simulation of detector response is a vital aspect of data analysis in particle physics, but current Monte Carlo methods are computationally expensive. Machine learning methods, which learn a mapping from incident particle to detector response, are much faster but require a model for every detector element with unique geometry. Complex geometries may require many models, each with their own training samples and hyperparameter tuning tasks. A promising approach is the use of geometry-aware models, which condition the response on the geometry, but current efforts typically require cumbersome full geometry specification. We present a geometry-aware model that takes advantage of the regularity of detector segments, requiring only the definition of cell sizes across regular segments. This model outperforms the current state of the art by over 70% across several key metrics including the Wasserstein distance metric.