Asymptotic behaviour of a family of gradient algorithms in R^ d and Hilbert spaces
From MaRDI portal
Publication:2492701
Abstract: The asymptotic behaviour of a family of gradient algorithms (including the methods of steepest descent and minimum residues) for the optimisation of bounded quadratic operators in R^d and Hilbert spaces is analyzed. The results obtained generalize those of Akaike (1959) in several directions. First, all algorithms in the family are shown to have the same asymptotic behaviour (convergence to a two-point attractor), which implies in particular that they have similar asymptotic convergence rates. Second, the analysis also covers the Hilbert space case. A detailed analysis of the stability property of the attractor is provided.
Recommendations
- Gradient algorithms for quadratic optimization with fast convergence rates
- The asymptotic behaviour of the \(s\)-step method of steepest descent for minimizing a quadratic functional in Hilbert space
- scientific article; zbMATH DE number 5119129
- Renormalised steepest descent in Hilbert space converges to a two-point attractor.
- On the gradient method in a Hilbert space in the case of nonisolated minima
Cites work
- A spectral conjugate gradient method for unconstrained optimization
- scientific article; zbMATH DE number 3734989 (Why is no real title available?)
- scientific article; zbMATH DE number 3760758 (Why is no real title available?)
- scientific article; zbMATH DE number 47028 (Why is no real title available?)
- scientific article; zbMATH DE number 3466802 (Why is no real title available?)
- scientific article; zbMATH DE number 3568468 (Why is no real title available?)
- scientific article; zbMATH DE number 1346777 (Why is no real title available?)
- Kantorovich-type inequalities for operators via \(D\)-optimal design theory
- On a successive transformation of probability distribution and its application to the analysis of the optimum gradient method
- On the asymptotic directions of the s-dimensional optimum gradient method
- On the behavior of the gradient norm in the steepest descent method
- Relaxed steepest descent and Cauchy-Barzilai-Borwein method
- Renormalised steepest descent in Hilbert space converges to a two-point attractor.
- The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem
- The Equivalence of Two Extremum Problems
- Two-Point Step Size Gradient Methods
Cited in
(12)- The asymptotic behaviour of the \(s\)-step method of steepest descent for minimizing a quadratic functional in Hilbert space
- On the asymptotic convergence and acceleration of gradient methods
- Fast gradient methods with alignment for symmetric linear systems without using Cauchy step
- Optimal experimental design and some related control problems
- Studying the rate of convergence of the steepest descent optimisation algorithm with relaxation
- An asymptotically optimal gradient algorithm for quadratic optimization with low computational cost
- scientific article; zbMATH DE number 3921652 (Why is no real title available?)
- Estimation of spectral bounds in gradient algorithms
- Gradient algorithms for quadratic optimization with fast convergence rates
- Delayed gradient methods for symmetric and positive definite linear systems
- Renormalised steepest descent in Hilbert space converges to a two-point attractor.
- On a family of relaxed gradient descent methods for strictly convex quadratic minimization
This page was built for publication: Asymptotic behaviour of a family of gradient algorithms in \(\mathbb R^{ d }\) and Hilbert spaces
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2492701)
