Global Convergence and Asymptotic Optimality of the Heavy Ball Method for a Class of Nonconvex Optimization Problems

V. Ugrinovskii; I. R. Petersen; I. Shames

doi:10.1109/LCSYS.2022.3163408

Global Convergence and Asymptotic Optimality of the Heavy Ball Method for a Class of Nonconvex Optimization Problems

V. Ugrinovskii, I. R. Petersen, I. Shames^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

Abstract

In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that render the method globally convergent and yield the best R-convergence factor. We show that for this family of functions, this convergence factor is superior to the factor obtained from the triple momentum method.

Original language	English
Pages (from-to)	2449-2454
Number of pages	6
Journal	IEEE Control Systems Letters
Volume	6
DOIs	https://doi.org/10.1109/LCSYS.2022.3163408
Publication status	Published - 2022

Access to Document

10.1109/LCSYS.2022.3163408

Cite this

@article{18cb3853bef2424cb7048be16e9414c1,

title = "Global Convergence and Asymptotic Optimality of the Heavy Ball Method for a Class of Nonconvex Optimization Problems",

abstract = "In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that render the method globally convergent and yield the best R-convergence factor. We show that for this family of functions, this convergence factor is superior to the factor obtained from the triple momentum method.",

keywords = "Optimization algorithms, robust control",

author = "V. Ugrinovskii and Petersen, \{I. R.\} and I. Shames",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2022",

doi = "10.1109/LCSYS.2022.3163408",

language = "English",

volume = "6",

pages = "2449--2454",

journal = "IEEE Control Systems Letters",

issn = "2475-1456",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Global Convergence and Asymptotic Optimality of the Heavy Ball Method for a Class of Nonconvex Optimization Problems

AU - Ugrinovskii, V.

AU - Petersen, I. R.

AU - Shames, I.

PY - 2022

Y1 - 2022

N2 - In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that render the method globally convergent and yield the best R-convergence factor. We show that for this family of functions, this convergence factor is superior to the factor obtained from the triple momentum method.

AB - In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that render the method globally convergent and yield the best R-convergence factor. We show that for this family of functions, this convergence factor is superior to the factor obtained from the triple momentum method.

KW - Optimization algorithms

KW - robust control

UR - https://www.scopus.com/pages/publications/85127504811

U2 - 10.1109/LCSYS.2022.3163408

DO - 10.1109/LCSYS.2022.3163408

M3 - Article

SN - 2475-1456

VL - 6

SP - 2449

EP - 2454

JO - IEEE Control Systems Letters

JF - IEEE Control Systems Letters

ER -

Global Convergence and Asymptotic Optimality of the Heavy Ball Method for a Class of Nonconvex Optimization Problems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this