English

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].

Keywords

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}
}
R2 v1 2026-06-23T08:18:12.665Z