Keywords: bayesian machine learning, markov chain monte carlo
TL;DR: A theoretical and empirical investigation of nonlinear markov chain monte carlo with applications to Bayesian machine learning.
Abstract: We explore the application of a nonlinear MCMC technique first introduced in  to problems in Bayesian machine learning. We provide a convergence guarantee in total variation that uses novel results for long-time convergence and large-particle (``propagation of chaos'') convergence. We apply this nonlinear MCMC technique to sampling problems including a Bayesian neural network on CIFAR10.
Supplementary Material: zip