Stochastic Cubic Regularization for Fast Nonconvex Optimization
Machine Learning
2017-12-07 v2 Optimization and Control
Machine Learning
Abstract
This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general smooth, nonconvex functions in only stochastic gradient and stochastic Hessian-vector product evaluations. The latter can be computed as efficiently as stochastic gradients. This improves upon the rate of stochastic gradient descent. Our rate matches the best-known result for finding local minima without requiring any delicate acceleration or variance-reduction techniques.
Cite
@article{arxiv.1711.02838,
title = {Stochastic Cubic Regularization for Fast Nonconvex Optimization},
author = {Nilesh Tripuraneni and Mitchell Stern and Chi Jin and Jeffrey Regier and Michael I. Jordan},
journal= {arXiv preprint arXiv:1711.02838},
year = {2017}
}
Comments
The first two authors contributed equally