Worst-Case Convergence Analysis of Inexact Gradient and Newton Methods Through Semidefinite Programming Performance Estimation - Archive ouverte HAL Access content directly
Journal Articles SIAM Journal on Optimization Year : 2020

Worst-Case Convergence Analysis of Inexact Gradient and Newton Methods Through Semidefinite Programming Performance Estimation

(1) , (2) , (3)
1
2
3

Abstract

We provide new tools for worst-case performance analysis of the gradient (or steepest descent) method of Cauchy for smooth strongly convex functions, and Newton's method for self-concordant functions, including the case of inexact search directions. The analysis uses semidefinite programming performance estimation, as pioneered by Drori and Teboulle [it Math. Program., 145 (2014), pp. 451--482], and extends recent performance estimation results for the method of Cauchy by the authors [it Optim. Lett., 11 (2017), pp. 1185--1199]. To illustrate the applicability of the tools, we demonstrate a novel complexity analysis of short step interior point methods using inexact search directions. As an example in this framework, we sketch how to give a rigorous worst-case complexity analysis of a recent interior point method by Abernethy and Hazan [it PMLR, 48 (2016), pp. 2520--2528].
Fichier principal
Vignette du fichier
1709.05191.pdf (480.29 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02956367 , version 1 (07-10-2020)

Identifiers

Cite

Etienne de Klerk, François Glineur, Adrien Taylor. Worst-Case Convergence Analysis of Inexact Gradient and Newton Methods Through Semidefinite Programming Performance Estimation. SIAM Journal on Optimization, 2020, 30 (3), pp.2053-2082. ⟨10.1137/19M1281368⟩. ⟨hal-02956367⟩
189 View
113 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More