English

Accelerating Incremental Gradient Optimization with Curvature Information

Optimization and Control 2020-03-02 v2 Machine Learning

Abstract

This paper studies an acceleration technique for incremental aggregated gradient ({\sf IAG}) method through the use of \emph{curvature} information for solving strongly convex finite sum optimization problems. These optimization problems of interest arise in large-scale learning applications. Our technique utilizes a curvature-aided gradient tracking step to produce accurate gradient estimates incrementally using Hessian information. We propose and analyze two methods utilizing the new technique, the curvature-aided IAG ({\sf CIAG}) method and the accelerated CIAG ({\sf A-CIAG}) method, which are analogous to gradient method and Nesterov's accelerated gradient method, respectively. Setting κ\kappa to be the condition number of the objective function, we prove the RR linear convergence rates of 14c0κ(κ+1)21 - \frac{4c_0 \kappa}{(\kappa+1)^2} for the {\sf CIAG} method, and 1c12κ1 - \sqrt{\frac{c_1}{2\kappa}} for the {\sf A-CIAG} method, where c0,c11c_0,c_1 \leq 1 are constants inversely proportional to the distance between the initial point and the optimal solution. When the initial iterate is close to the optimal solution, the RR linear convergence rates match with the gradient and accelerated gradient method, albeit {\sf CIAG} and {\sf A-CIAG} operate in an incremental setting with strictly lower computation complexity. Numerical experiments confirm our findings. The source codes used for this paper can be found on \url{http://github.com/hoitowai/ciag/}.

Keywords

Cite

@article{arxiv.1806.00125,
  title  = {Accelerating Incremental Gradient Optimization with Curvature Information},
  author = {Hoi-To Wai and Wei Shi and Cesar A. Uribe and Angelia Nedich and Anna Scaglione},
  journal= {arXiv preprint arXiv:1806.00125},
  year   = {2020}
}

Comments

22 pages, 3 figures, 3 tables. Accepted by Computational Optimization and Applications, to appear

R2 v1 2026-06-23T02:15:29.327Z