A Hybrid Stochastic Gradient Hamiltonian Monte Carlo Method
A Hybrid Stochastic Gradient Hamiltonian Monte Carlo Method
Recent theoretical analyses reveal that existing Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods need large mini-batches of samples (exponentially dependent on the dimension) to reduce the mean square error of gradient estimates and ensure non-asymptotic convergence guarantees when the target distribution has a nonconvex potential function. In this paper, …