Non-asymptotic superlinear convergence of standard quasi-Newton methods

DOI10.1007/s10107-022-01887-4zbMath1519.90171arXiv2003.13607OpenAlexW3013599873WikidataQ114228402 ScholiaQ114228402MaRDI QIDQ6044985

Aryan Mokhtari, Qiujiang Jin

Publication date: 25 May 2023

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.13607

zbMATH Keywords

quasi-Newton methodBFGS algorithmsuperlinear convergence rateDFP algorithmnon-asymptotic analysis

Mathematics Subject Classification ID

Convex programming (90C25) Methods of quasi-Newton type (90C53)

Related Items (max. 100)

Hessian averaging in stochastic Newton methods achieves superlinear convergence

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the limited memory BFGS method for large scale optimization
• Convergence theory for the structured BFGS secant method with an application to nonlinear least squares
• Convergence of quasi-Newton matrices generated by the symmetric rank one update
• Global and superlinear convergence of a restricted class of self-scaling methods with inexact line searches, for convex functions
• Introductory lectures on convex optimization. A basic course.
• Local convergence analysis for partitioned quasi-Newton updates
• New results on superlinear convergence of classical quasi-Newton methods
• Rates of superlinear convergence for classical quasi-Newton methods
• Local and superlinear convergence of quasi-Newton methods based on modified secant conditions
• Cubic regularization of Newton method and its global performance
• A Modified BFGS Algorithm for Unconstrained Optimization
• Global Convergence of a Cass of Quasi-Newton Methods on Convex Problems
• Some Convergence Properties of Broyden’s Method
• Updating Quasi-Newton Matrices with Limited Storage
• Variable Metric Method for Minimization
• On the Global Convergence of Broyden's Method
• Trust Region Methods
• Quasi-Newton methods: superlinear convergence without line searches for self-concordant functions
• A Globally and Superlinearly Convergent Gauss--Newton-Based BFGS Method for Symmetric Nonlinear Equations
• On the Local and Superlinear Convergence of Quasi-Newton Methods
• A Characterization of Superlinear Convergence and Its Application to Quasi-Newton Methods
• A Class of Methods for Solving Nonlinear Simultaneous Equations
• A Rapidly Convergent Descent Method for Minimization
• A Family of Variable-Metric Methods Derived by Variational Means
• A new approach to variable metric algorithms
• The Convergence of Single-Rank Quasi-Newton Methods
• On the Convergence of the Variable Metric Algorithm
• Conditioning of Quasi-Newton Methods for Function Minimization
• IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate
• Greedy Quasi-Newton Methods with Explicit Superlinear Convergence

This page was built for publication: Non-asymptotic superlinear convergence of standard quasi-Newton methods