English

Stochastic Recursive Gradient Algorithm for Nonconvex Optimization

Machine Learning 2017-05-23 v1 Machine Learning Optimization and Control

Abstract

In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general nonconvex functions and a linear convergence rate for gradient dominated functions, both of which have some advantages compared to other modern stochastic gradient algorithms for nonconvex losses.

Keywords

Cite

@article{arxiv.1705.07261,
  title  = {Stochastic Recursive Gradient Algorithm for Nonconvex Optimization},
  author = {Lam M. Nguyen and Jie Liu and Katya Scheinberg and Martin Takáč},
  journal= {arXiv preprint arXiv:1705.07261},
  year   = {2017}
}