New Results on Superlinear Convergence of Classical Quasi-Newton Methods
(2021) Journal of Optimization Theory and Applications — Vol. 188, n° 3, p. 744-769 (2021)
Files
CORE_RP_3249.pdf
Open Access - Adobe PDF
- 718.27 KB
Details
- Authors
- 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.
- Affiliations
Citations
Rodomanov, A., & Nesterov, Y. (2021). New Results on Superlinear Convergence of Classical Quasi-Newton Methods. Journal of Optimization Theory and Applications, 188(3), 744-769. https://doi.org/10.1007/s10957-020-01805-8 (Original work published 2021)