Improved Neural Network Monte Carlo Simulation

TL;DR

This paper enhances a neural network-based Monte Carlo simulation for particle decay processes, achieving high accuracy and efficiency while addressing numerical stability and bijectivity issues.

Contribution

It introduces improved training algorithms for neural network Monte Carlo simulations, ensuring better stability and near-bijective mappings for accurate particle decay modeling.

Findings

Integrated decay width within 0.7% of true value

Unweighting efficiency of 26% achieved

Neural network approximates bijective mappings effectively

Abstract

The algorithm for Monte Carlo simulation of parton-level events based on an Artificial Neural Network (ANN) proposed in arXiv:1810.11509 is used to perform a simulation of $H\to 4\ell$ decay. Improvements in the training algorithm have been implemented to avoid numerical instabilities. The integrated decay width evaluated by the ANN is within 0.7% of the true value and unweighting efficiency of 26% is reached. While the ANN is not automatically bijective between input and output spaces, which can lead to issues with simulation quality, we argue that the training procedure naturally prefers bijective maps, and demonstrate that the trained ANN is bijective to a very good approximation.