Explicit Superlinear Convergence Rates of The SR1 Algorithm
Abstract
We study the convergence rate of the famous Symmetric Rank-1 (SR1) algorithm which has wide applications in different scenarios. Although it has been extensively investigated, SR1 still lacks a non-asymptotic superlinear rate compared with other quasi-Newton methods such as DFP and BFGS. In this paper we address this problem. Inspired by the recent work on explicit convergence analysis of quasi-Newton methods, we obtain the first explicit non-asymptotic rates of superlinear convergence for the vanilla SR1 methods with correction strategy to achieve the numerical stability. Specifically, the vanilla SR1 with the correction strategy achieves the rates of the form for general smooth strongly-convex functions where is the iteration counter, is the condition number of the objective function and is the dimension of the problem. For the quadratic function, the vanilla SR1 algorithm can find the optima of the objective function at most steps.
Keywords
Cite
@article{arxiv.2105.07162,
title = {Explicit Superlinear Convergence Rates of The SR1 Algorithm},
author = {Haishan Ye and Dachao Lin and Zhihua Zhang and Xiangyu Chang},
journal= {arXiv preprint arXiv:2105.07162},
year = {2021}
}