arXiv Analytics

Sign in

arXiv:2001.09285 [math.OC]AbstractReferencesReviewsResources

Pactical Newton Methods for Electronic Structure Calculations

Xiaoying Dai, Liwei Zhang, Aihui Zhou

Published 2020-01-25Version 1

In this paper, we propose and analyze some practical Newton methods for electronic structure calculations. We show the convergence and the local quadratic convergence rate for the Newton method when the Newton search directions are well-obtained. In particular, we investigate some basic implementation issues in determining the search directions and step sizes which ensures the convergence of the subproblem at each iteration and accelerates the algorithm, respectively. It is shown by our numerical experiments that our Newton methods perform better than the existing conjugate gradient method, and the Newton method with the adaptive step size strategy is even more efficient.

Related articles: Most relevant | Search more
arXiv:1708.08048 [math.OC] (Published 2017-08-27)
A Semi-smooth Newton Method for Solving Semidefinite Programs in Electronic Structure Calculations
arXiv:2412.03319 [math.OC] (Published 2024-12-04)
Comparison between tensor methods and neural networks in electronic structure calculations
arXiv:2211.00140 [math.OC] (Published 2022-10-31)
A Damped Newton Method Achieves Global $O\left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate