Corpus ID: 30924997

Stochastic Recursive Gradient Algorithm for Nonconvex Optimization

@article{Nguyen2017StochasticRG,
  title={Stochastic Recursive Gradient Algorithm for Nonconvex Optimization},
  author={Lam M. Nguyen and J. Liu and K. Scheinberg and Martin Tak{\'a}c},
  journal={ArXiv},
  year={2017},
  volume={abs/1705.07261}
}

Lam M. Nguyen, J. Liu, +1 author Martin Takác

Published 2017

Computer Science, Mathematics

ArXiv

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… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed