Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics
Fan Chen, Yiqing Lin, Zhenjie Ren, Songbo Wang
Abstract
We study the kinetic mean field Langevin dynamics under the functional convexity assumption of the mean field energy functional. Using hypocoercivity, we first establish the exponential convergence of the mean field dynamics and then show the corresponding N-particle system converges exponentially in a rate uniform in N modulo a small error. Finally we study the short-time regularization effects of the dynamics and prove its uniform-in-time propagation of chaos property in both the Wasserstein and entropic sense. Our results can be applied to the training of two-layer neural networks with momentum and we include the numerical experiments.
Topics & Concepts
MathematicsLangevin dynamicsConvexityMean field theoryStatistical physicsExponential functionKinetic energyMathematical analysisApplied mathematicsClassical mechanicsPhysicsQuantum mechanicsStatisticsFinancial economicsEconomicsModel Reduction and Neural NetworksAdvanced Thermodynamics and Statistical MechanicsStatistical Mechanics and Entropy