Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization

TL;DR

This paper introduces a tensor decomposition approach within generative models to efficiently produce multidimensional simulation data, significantly reducing computational costs while maintaining data usefulness.

Contribution

It presents a novel method of generating tensor factors instead of full tensors in generative models, enhancing efficiency for multidimensional data generation.

Findings

Reduced computational costs in data generation

Maintained data quality and usefulness

Applicable to complex multidimensional datasets

Abstract

Producing large complex simulation datasets can often be a time and resource consuming task. Especially when these experiments are very expensive, it is becoming more reasonable to generate synthetic data for downstream tasks. Recently, these methods may include using generative machine learning models such as Generative Adversarial Networks or diffusion models. As these generative models improve efficiency in producing useful data, we introduce an internal tensor decomposition to these generative models to even further reduce costs. More specifically, for multidimensional data, or tensors, we generate the smaller tensor factors instead of the full tensor, in order to significantly reduce the model's output and overall parameters. This reduces the costs of generating complex simulation data, and our experiments show the generated data remains useful. As a result, tensor decomposition has the potential to improve efficiency in generative models, especially when generating multidimensional data, or tensors.