Quasi-Newton methods: superlinear convergence without line searches for self-concordant functions

DOI10.1080/10556788.2018.1510927zbMath1409.90091arXiv1612.06965OpenAlexW2563719283MaRDI QIDQ4646680

Wenbo Gao, Donald Goldfarb

Publication date: 14 January 2019

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1612.06965

zbMATH Keywords

quasi-Newton methodsBFGSself-concordant functionsdamped Newton method

Mathematics Subject Classification ID

Methods of quasi-Newton type (90C53) Search theory (90B40)

Related Items

Rates of superlinear convergence for classical quasi-Newton methods, Sketched Newton--Raphson, Non-asymptotic superlinear convergence of standard quasi-Newton methods, Optimal step length for the maximal decrease of a self-concordant function by the Newton method, Extended artificial neural networks approach for solving two-dimensional fractional-order Volterra-type integro-differential equations, Greedy PSB methods with explicit superlinear convergence, Composite convex optimization with global and local inexact oracles, New results on superlinear convergence of classical quasi-Newton methods, Optimal step length for the Newton method: case of self-concordant functions, Generalized self-concordant functions: a recipe for Newton-type methods, Greedy Quasi-Newton Methods with Explicit Superlinear Convergence

Uses Software

• L-BFGS
• LIBSVM
• ve08

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Stochastic Quasi-Newton Method for Large-Scale Optimization
• On the limited memory BFGS method for large scale optimization
• Introductory lectures on convex optimization. A basic course.
• Local convergence analysis for partitioned quasi-Newton updates
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Global Convergence of a Cass of Quasi-Newton Methods on Convex Problems
• Updating Quasi-Newton Matrices with Limited Storage
• Block BFGS Methods
• A Characterization of Superlinear Convergence and Its Application to Quasi-Newton Methods
• A Rapidly Convergent Descent Method for Minimization
• Composite Self-Concordant Minimization
• Quasi-Newton Methods and their Application to Function Minimisation
• A Family of Variable-Metric Methods Derived by Variational Means
• A new approach to variable metric algorithms
• Conditioning of Quasi-Newton Methods for Function Minimization