We introduce a novel machine learning method developed for the fast simulation of calorimeter detector response, adapting vector-quantized variational autoencoder (VQ-VAE). Our model adopts a two-stage generation strategy: initially compressing geometry-aware calorimeter data into a discrete latent space, followed by the application of a sequence model to learn and generate the latent tokens. Extensive experimentation on the Calo-challenge dataset underscores the efficiency of our approach, showcasing a remarkable improvement in the generation speed compared with conventional method by a factor of 2000. Remarkably, our model achieves the generation of calorimeter showers within milliseconds. Furthermore, comprehensive quantitative evaluations across various metrics are performed to validate physics performance of generation.
Cite
@article{arxiv.2405.06605,
title = {Calo-VQ: Vector-Quantized Two-Stage Generative Model in Calorimeter Simulation},
author = {Qibin Liu and Chase Shimmin and Xiulong Liu and Eli Shlizerman and Shu Li and Shih-Chieh Hsu},
journal= {arXiv preprint arXiv:2405.06605},
year = {2024}
}