Advancing Set-Conditional Set Generation: Diffusion Models for Fast Simulation of Reconstructed Particles

TL;DR

This paper introduces a diffusion model-based method for fast, accurate simulation of reconstructed particles conditioned on input sets, significantly improving efficiency in collider data analysis.

Contribution

It advances set-conditional set generation with diffusion models, enabling rapid simulation and reconstruction of particle sets in collider experiments.

Findings

Diffusion models accurately reproduce complex particle spectra.

The approach significantly reduces simulation time.

Effective in realistic detector simulation scenarios.

Abstract

The computational intensity of detector simulation and event reconstruction poses a significant difficulty for data analysis in collider experiments. This challenge inspires the continued development of machine learning techniques to serve as efficient surrogate models. We propose a fast emulation approach that combines simulation and reconstruction. In other words, a neural network generates a set of reconstructed objects conditioned on input particle sets. To make this possible, we advance set-conditional set generation with diffusion models. Using a realistic, generic, and public detector simulation and reconstruction package (COCOA), we show how diffusion models can accurately model the complex spectrum of reconstructed particles inside jets.