Neural Network-Based Approach to Phase Space Integration

TL;DR

This paper introduces a neural network algorithm for phase space integration in particle physics, demonstrating superior efficiency and flexibility over traditional methods like VEGAS, especially in complex scenarios with sharp features.

Contribution

The paper presents a novel neural network-based method for phase space integration that outperforms traditional algorithms in efficiency and adaptability to complex features.

Findings

Achieved unweighting efficiencies of 30% to 75%.

Performed well on complex phase space features like resonances.

Does not require phase space coordinate alignment.

Abstract

Monte Carlo methods are widely used in particle physics to integrate and sample probability distributions (differential cross sections or decay rates) on multi-dimensional phase spaces. We present a Neural Network (NN) algorithm optimized to perform this task. The algorithm has been applied to several examples of direct relevance for particle physics, including situations with non-trivial features such as sharp resonances and soft/collinear enhancements. Excellent performance has been demonstrated in all examples, with the properly trained NN achieving unweighting efficiencies of between 30% and 75%. In contrast to traditional Monte Carlo algorithms such as VEGAS, the NN-based approach does not require that the phase space coordinates be aligned with resonant or other features in the cross section.