Convergence of First-Order Algorithms with Momentum from the Perspective of an Inexact Gradient Descent Method

Pham Duy Khanh (), Boris S. Mordukhovich () and Dat Ba Tran ()
Additional contact information
Pham Duy Khanh: Ho Chi Minh City University of Education
Boris S. Mordukhovich: Wayne State University
Dat Ba Tran: Rowan University

Journal of Optimization Theory and Applications, 2026, vol. 208, issue 1, No 40, 38 pages

Abstract: Abstract This paper introduces a novel inexact gradient descent method with momentum (IGDm) considered as a general framework for various first-order methods with momentum. This includes, in particular, the inexact proximal point method (IPPm), extragradient method (EGm) coming from variational inequalities, and sharpness-aware minimization (SAMm). Asymptotic convergence properties of IGDm are established under both global and local assumptions on objective functions with providing constructive convergence rates depending on the Polyak-Łojasiewicz-Kurdyka (PLK) conditions for the objective function. Global convergence of EGm and SAMm for general smooth functions and of IPPM for weakly convex functions is derived in this way. Moreover, local convergence properties of EGm and SAMm for locally smooth functions as well as of IPPm for prox-regular functions are established. Numerical experiments for derivative-free optimization problems are conducted to confirm the efficiency of the momentum effects of the developed methods under the inexactness of gradient computations.

Keywords: Inexact gradient descent and proximal point methods; Extragradient method; Sharpness-aware minimization; Machine learning; Momentum; Global and local convergence; Local convergence; 90C52; 90C56; 49J53; 90C25; 90C26 (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-025-02864-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joptap:v:208:y:2026:i:1:d:10.1007_s10957-025-02864-5

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1007/s10957-025-02864-5

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().