English

Inexact Non-Convex Newton-Type Methods

Optimization and Control 2018-02-21 v1

Abstract

For solving large-scale non-convex problems, we propose inexact variants of trust region and adaptive cubic regularization methods, which, to increase efficiency, incorporate various approximations. In particular, in addition to approximate sub-problem solves, both the Hessian and the gradient are suitably approximated. Using rather mild conditions on such approximations, we show that our proposed inexact methods achieve similar optimal worst-case iteration complexities as the exact counterparts. Our proposed algorithms, and their respective theoretical analysis, do not require knowledge of any unknowable problem-related quantities, and hence are easily implementable in practice. In the context of finite-sum problems, we then explore randomized sub-sampling methods as ways to construct the gradient and Hessian approximations and examine the empirical performance of our algorithms on some real datasets.

Keywords

Cite

@article{arxiv.1802.06925,
  title  = {Inexact Non-Convex Newton-Type Methods},
  author = {Zhewei Yao and Peng Xu and Farbod Roosta-Khorasani and Michael W. Mahoney},
  journal= {arXiv preprint arXiv:1802.06925},
  year   = {2018}
}

Comments

36 pages, 2 figures

R2 v1 2026-06-23T00:27:07.855Z