Neural Network-Based Approach to Phase Space Integration
This addresses a computational bottleneck for particle physics simulations, offering a novel alternative to traditional Monte Carlo methods like VEGAS.
The paper tackles the problem of integrating and sampling probability distributions in multi-dimensional phase spaces in particle physics, using a neural network algorithm that achieves unweighting efficiencies of 30% to 75% without requiring alignment with features like resonances.
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.