New Results on Superlinear Convergence of Classical Quasi-Newton Methods
Optimization and Control
2021-06-02 v3
Abstract
We present a new theoretical analysis of local superlinear convergence of classical quasi-Newton methods from the convex Broyden class. As a result, we obtain a significant improvement in the currently known estimates of the convergence rates for these methods. In particular, we show that the corresponding rate of the Broyden-Fletcher-Goldfarb-Shanno method depends only on the product of the dimensionality of the problem and the logarithm of its condition number.
Keywords
Cite
@article{arxiv.2004.14866,
title = {New Results on Superlinear Convergence of Classical Quasi-Newton Methods},
author = {Anton Rodomanov and Yurii Nesterov},
journal= {arXiv preprint arXiv:2004.14866},
year = {2021}
}
Comments
J Optim Theory Appl (2021). arXiv admin note: text overlap with arXiv:2003.09174