Block BFGS Methods
Optimization and Control
2017-12-04 v3
Abstract
We introduce a quasi-Newton method with block updates called Block BFGS. We show that this method, performed with inexact Armijo-Wolfe line searches, converges globally and superlinearly under the same convexity assumptions as BFGS. We also show that Block BFGS is globally convergent to a stationary point when applied to non-convex functions with bounded Hessian, and discuss other modifications for non-convex minimization. Numerical experiments comparing Block BFGS, BFGS and gradient descent are presented.
Keywords
Cite
@article{arxiv.1609.00318,
title = {Block BFGS Methods},
author = {Wenbo Gao and Donald Goldfarb},
journal= {arXiv preprint arXiv:1609.00318},
year = {2017}
}
Comments
To appear in SIAM J. Optim. 28 pages, 4 figures