Huy N. Chau, Miklos Rasonyi
Published 2019-03-25Version 1
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].
Optimizing Cox Models with Stochastic Gradient Descent: Theoretical Foundations and Practical Guidances
Stochastic Gradient Descent in Hilbert Scales: Smoothness, Preconditioning and Earlier Stopping
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
![QR code for arXiv:1903.10328 [stat.ML]](http://oss.arxitics.com/images/favicon.svg)