Solving the QCD effective kinetic theory with neural networks

TL;DR

This paper introduces a neural network approach to efficiently estimate the collision integral in QCD kinetic theory, significantly reducing computational costs and enabling detailed event-by-event simulations of heavy-ion collisions.

Contribution

The authors develop a neural network model that accurately predicts the collision integral in QCD kinetic theory, accelerating simulations compared to traditional Monte Carlo methods.

Findings

Neural network accurately predicts the collision integral for isotropic and anisotropic distributions.

The method reduces computational time for collision integral evaluation.

The approach enables detailed event-by-event modeling of pre-equilibrium stages in heavy-ion collisions.

Abstract

Event-by-event QCD kinetic theory simulations are hindered by the large numerical cost of evaluating the high-dimensional collision integral in the Boltzmann equation. In this work, we show that a neural network can be used to obtain an accurate estimate of the collision integral in a fraction of the time required for the ordinary Monte Carlo evaluation of the integral. We demonstrate that for isotropic and anisotropic distribution functions, the network accurately predicts the time evolution of the distribution function, which we verify by performing traditional evaluations of the collision integral and comparing several moments of the distribution function. This work sets the stage for an event-by-event modeling of the pre-equilibrium initial stages in heavy-ion collisions.