MLLGMar 25, 2019

Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Learning

arXiv:1903.10328v313 citations
Originality Synthesis-oriented
AI Analysis

It addresses convergence guarantees for a stochastic optimization method in non-convex settings, which is incremental as it builds on existing analyses.

The paper provides non-asymptotic convergence analysis for Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) in non-convex optimization, improving upon prior work such as [GGZ18].

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].

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes