CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds

TL;DR

CaloMan introduces a novel approach to rapidly generate realistic calorimeter showers by learning their low-dimensional manifold structure and estimating data density, significantly improving simulation efficiency at the Large Hadron Collider.

Contribution

The paper presents a new method that models calorimeter showers through manifold learning and density estimation, enabling faster and more efficient simulations compared to existing techniques.

Findings

Reduces simulation time by leveraging low-dimensional manifold structure.

Achieves realistic shower generation with high fidelity.

Outperforms traditional physics-based and generative models in speed.

Abstract

Precision measurements and new physics searches at the Large Hadron Collider require efficient simulations of particle propagation and interactions within the detectors. The most computationally expensive simulations involve calorimeter showers. Advances in deep generative modelling - particularly in the realm of high-dimensional data - have opened the possibility of generating realistic calorimeter showers orders of magnitude more quickly than physics-based simulation. However, the high-dimensional representation of showers belies the relative simplicity and structure of the underlying physical laws. This phenomenon is yet another example of the manifold hypothesis from machine learning, which states that high-dimensional data is supported on low-dimensional manifolds. We thus propose modelling calorimeter showers first by learning their manifold structure, and then estimating the density of data across this manifold. Learning manifold structure reduces the dimensionality of the data, which enables fast training and generation when compared with competing methods.