English

Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods

Optimization and Control 2022-09-13 v5

Abstract

Optimization is important in machine learning problems, and quasi-Newton methods have a reputation as the most efficient numerical schemes for smooth unconstrained optimization. In this paper, we consider the explicit superlinear convergence rates of quasi-Newton methods and address two open problems mentioned by Rodomanov and Nesterov. First, we extend Rodomanov and Nesterov's results to random quasi-Newton methods, which include common DFP, BFGS, SR1 methods. Such random methods adopt a random direction for updating the approximate Hessian matrix in each iteration. Second, we focus on the specific quasi-Newton methods: SR1 and BFGS methods. We provide improved versions of greedy and random methods with provable better explicit (local) superlinear convergence rates. Our analysis is closely related to the approximation of a given Hessian matrix, unconstrained quadratic objective, as well as the general strongly convex, smooth, and strongly self-concordant functions.

Keywords

Cite

@article{arxiv.2104.08764,
  title  = {Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods},
  author = {Dachao Lin and Haishan Ye and Zhihua Zhang},
  journal= {arXiv preprint arXiv:2104.08764},
  year   = {2022}
}

Comments

Fix some typos, 40 pages, 3 figures, final version