On the Linear Convergence of the Cauchy Algorithm for a Class of Restricted Strongly Convex Functions

2016/11/01 by Hui Zhang, Zhang, Hui
Computer Science · Mathematics · #Advanced Optimization Algorithms Research #Approximation Theory and Sequence Spaces #FOS: Mathematics #Optimization and Control (math.OC) #Optimization and Variational Analysis

paper · pdf · doi:10.48550/arxiv.1611.00090

openalex publication_date 2016/11/01 · openalex created_date 2016/11/11 · openalex updated_date 2026/07/28

Abstract

In this short note, we extend the linear convergence result of the Cauchy algorithm, derived recently by E. Klerk, F. Glineur, and A. Taylor, from the case of smooth strongly convex functions to the case of restricted strongly convex functions with certain form.

Citations

• Gradient methods for convex minimization: better rates under weaker conditions
• Linear convergence of first order methods for non-strongly convex optimization

Related

• The restricted strong convexity revisited: Analysis of equivalence to error bound and quadratic growth
• Linear convergence of first order methods for non-strongly convex optimization
• A note on the optimal convergence rate of descent methods with fixed step sizes for smooth strongly convex functions
• Strongly convex functions, Moreau envelopes and the generic nature of convex functions with strong minimizers
• Strongly Convex Maximization via the Frank-Wolfe Algorithm with the Kurdyka-Łojasiewicz Inequality