Solving the QCD effective kinetic theory with neural networks

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.

14 pages, 7 figures, accepted for publication in EPJC

References in corpus (35)

• A high-bias, low-variance introduction to Machine Learning for physicists
• Transport coefficients in high temperature gauge theories: (II) Beyond leading log
• Derivation of transient relativistic fluid dynamics from the Boltzmann equation
• Photon and Gluon Emission in Relativistic Plasmas
• Applying Bayesian parameter estimation to relativistic heavy-ion collisions: simultaneous characterization of the initial state and quark-gluon plasma medium
• Simulating elliptic flow with viscous hydrodynamics
• Effective Kinetic Theory for High Temperature Gauge Theories
• Hydrodynamics Beyond the Gradient Expansion: Resurgence and Resummation
• Isotropization and hydrodynamization in weakly coupled heavy-ion collisions
• Bayesian analysis of heavy ion collisions with the heavy ion computational framework Trajectum
• Effective kinetic description of event-by-event pre-equilibrium dynamics in high-energy heavy-ion collisions
• Matching the Nonequilibrium Initial Stage of Heavy Ion Collisions to Hydrodynamics with QCD Kinetic Theory
• A simple sum rule for the thermal gluon spectral function and applications
• Approach to equilibrium in weakly coupled nonabelian plasmas
• The First fm/c of Heavy-Ion Collisions
• What attracts to attractors?
• Do nuclear collisions create a locally equilibrated quark-gluon plasma?
• UV Cascade in Classical Yang-Mills via Kinetic Theory
• Multi-messenger heavy-ion collision physics
• Chemical Equilibration in Hadronic Collisions
• Flow in AA and pA as an interplay of fluid-like and non-fluid like excitations
• Chemical Equilibration in Weakly Coupled QCD
• Non-equilibrium attractor in high-temperature QCD plasmas
• Nearly isentropic flow at sizeable $\eta /s$
• Opacity dependence of elliptic flow in kinetic theory
• Establishing the Range of Applicability of Hydrodynamics in High-Energy Collisions
• Using neural networks to accelerate the solution of the Boltzmann equation
• Hydrodynamization in systems with detailed transverse profiles
• Theoretical Aspects of Group Equivariant Neural Networks
• Opacity dependence of transverse flow, pre-equilibrium and applicability of hydrodynamics in heavy-ion collisions
• RelaxNet: A structure-preserving neural network to approximate the Boltzmann collision operator
• Causality violations in simulations of large and small heavy-ion collisions
• Limiting attractors in heavy-ion collisions
• Soft-gluon exchange matters: isotropic screening in QCD kinetic theory
• Collective dynamics in heavy and light-ion collisions -- I) Kinetic Theory vs. Hydrodynamics