R-linear convergence of the Barzilai and Borwein gradient method
By Yuhong Dai, L. Liao. 2002
339 citations recorded by the source corpus.
Subfields: Computational Mechanics, Computational Theory and Mathematics, Numerical Analysis
View Paper: https://www.semanticscholar.org/paper/d4c405a9b746206fe88f204377c921029364844d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Yuhong Dai
- Roger Fletcher
- Shiqian Ma
- Conghui Tan
- Yuqiu Qian
- Tom Goldstein
- Simon Lacoste-Julien
- G. Frassoldati
In Computational Theory and Mathematics
- Yuhong Dai
- Roger Fletcher
- Shiqian Ma
- Conghui Tan
- Yuqiu Qian
- William W. Hager
- Hongchao Zhang
- Sven Leyffer
In Numerical Analysis
- Yuhong Dai
- Shiqian Ma
- Yuqiu Qian
- Conghui Tan
- Roger Fletcher
- William W. Hager
- Hongchao Zhang
- Stephen J. Wright
Citations in the corpus
- Spectral residual method without gradient information for solving large-scale nonlinear systems of equations (2006, neutral): “gradient methods can be found in [8, 10, 24], among others.”
- On the Barzilai-Borwein Method (2005, methodology): “Also for quadratic functions, the BB method has been shown to converge ( Raydan (1993)), and convergence is R-linear ( Dai and Liao (1999) ).”
- Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming (2005, methodology): “In general, R-linear convergence has been established for the BB method by Dai and Liao [10] in the n−dimensional case.”
- Barzilai-Borwein Step Size for Stochastic Gradient Descent (2016, methodology): “For convergence analysis, generalizations and variants of the BB method, we refer the interested readers to [14, 15, 6, 9, 4, 5, 3] and references therein.”