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

Please sign up or login with your details

Forgot password? Click here to reset