Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning
Machine Learning
2020-02-26 v3 Machine Learning
Abstract
Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) is a momentum version of stochastic gradient descent with properly injected Gaussian noise to find a global minimum. In this paper, non-asymptotic convergence analysis of SGHMC is given in the context of non-convex optimization, where subsampling techniques are used over an i.i.d dataset for gradient updates. Our results complement those of [RRT17] and improve on those of [GGZ18].
Cite
@article{arxiv.1903.10328,
title = {Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning},
author = {Huy N. Chau and Miklos Rasonyi},
journal= {arXiv preprint arXiv:1903.10328},
year = {2020}
}