New results on superlinear convergence of classical quasi-Newton methods

DOI10.1007/s10957-020-01805-8zbMath1469.90160arXiv2004.14866OpenAlexW3023696268MaRDI QIDQ2031938

Yu. E. Nesterov, Anton Rodomanov

Publication date: 15 June 2021

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.14866

zbMATH Keywords

rate of convergencelocal convergencequasi-Newton methodssuperlinear convergenceBFGSDFPconvex Broyden class

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Nonlinear programming (90C30) Methods of quasi-Newton type (90C53)

Related Items

Towards explicit superlinear convergence rate for SR1 ⋮ Non-asymptotic superlinear convergence of standard quasi-Newton methods ⋮ Approximate Newton Policy Gradient Algorithms ⋮ A fast forward kinematics algorithm based on planar quaternion solution for a class of 3-DoF planar parallel mechanisms ⋮ Solving nonlinear equations with a direct Broyden method and its acceleration ⋮ Hessian averaging in stochastic Newton methods achieves superlinear convergence ⋮ Greedy PSB methods with explicit superlinear convergence

Uses Software

• L-BFGS
• ve08

Cites Work

• Unnamed Item
• Nonsmooth optimization via quasi-Newton methods
• On the limited memory BFGS method for large scale optimization
• The superlinear convergence of a modified BFGS-type method for unconstrained optimization
• Local convergence analysis for partitioned quasi-Newton updates
• Smoothness parameter of power of Euclidean norm
• Local and superlinear convergence of quasi-Newton methods based on modified secant conditions
• Global Convergence of a Cass of Quasi-Newton Methods on Convex Problems
• A Tool for the Analysis of Quasi-Newton Methods with Application to Unconstrained Minimization
• Superlinear convergence of Broyden's boundedθ-class of methods
• On the Behavior of Broyden’s Class of Quasi-Newton Methods
• Variable Metric Method for Minimization
• Local and Superlinear Convergence for Partially Known Quasi-Newton Methods
• Quasi-Newton Methods, Motivation and Theory
• LOCAL AND SUPERLINEAR CONVERGENCE OF STRUCTURED QUASI-NEWTON METHODS FOR NONLINEAR OPTIMIZATION
• Quasi-Newton methods: superlinear convergence without line searches for self-concordant functions
• On the Local and Superlinear Convergence of Quasi-Newton Methods
• A Characterization of Superlinear Convergence and Its Application to Quasi-Newton Methods
• A Rapidly Convergent Descent Method for Minimization
• Quasi-Newton Methods and their Application to Function Minimisation
• A Family of Variable-Metric Methods Derived by Variational Means
• The Convergence of a Class of Double-rank Minimization Algorithms
• A new approach to variable metric algorithms
• On the Convergence of the Variable Metric Algorithm
• The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations
• Conditioning of Quasi-Newton Methods for Function Minimization
• Quasi-newton algorithms generate identical points
• Quasi Newton techniques generate identical points II: The proofs of four new theorems
• IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate