DeepAI
Log In Sign Up

Ergodicity of the underdamped mean-field Langevin dynamics

07/29/2020
by   Anna Kazeykina, et al.
0

We study the long time behavior of an underdamped mean-field Langevin (MFL) equation, and provide a general convergence as well as an exponential convergence rate result under different conditions. The results on the MFL equation can be applied to study the convergence of the Hamiltonian gradient descent algorithm for the overparametrized optimization. We then provide a numerical example of the algorithm to train a generative adversarial networks (GAN).

READ FULL TEXT

page 1

page 2

page 3

page 4

01/25/2022

Convex Analysis of the Mean Field Langevin Dynamics

As an example of the nonlinear Fokker-Planck equation, the mean field La...
03/14/2021

Mean Field Game GAN

We propose a novel mean field games (MFGs) based GAN(generative adversar...
05/06/2021

On Linear Damping Around Inhomogeneous Stationary States of the Vlasov-HMF Model

We study the dynamics of perturbations around an inhomogeneous stationar...
05/14/2022

Trajectory Inference via Mean-field Langevin in Path Space

Trajectory inference aims at recovering the dynamics of a population fro...
06/03/2021

Influence Estimation and Maximization via Neural Mean-Field Dynamics

We propose a novel learning framework using neural mean-field (NMF) dyna...
04/06/2020

Game on Random Environement, Mean-field Langevin System and Neural Networks

In this paper we study a type of games regularized by the relative entro...
04/06/2020

Game on Random Environment, Mean-field Langevin System and Neural Networks

In this paper we study a type of games regularized by the relative entro...