Equivalence of the Polyak-Łojasiewicz-Kurdyka Exponent Via Difference-of-Moreau-Envelope Smoothing

Shuqin Sun ()
Additional contact information
Shuqin Sun: China West Normal University

Journal of Optimization Theory and Applications, 2026, vol. 208, issue 1, No 56, 30 pages

Abstract: Abstract For unconstrained nonsmooth difference-of-convex (DC) optimization problems, the difference-of-Moreau-envelope (DME) smoothing serves as a significant smooth approximation for them. Maintaining DC structure, the resulted DME-based model has a one-to-one correspondence for the stationary points with the original DC problem. This has led to the development of DME-specific algorithms to indirectly solve the DC problems by solving their DME-based models. In this paper, we obtain the global convergence and the specific local convergence rate of various DME-specific algorithms to find the stationary points of the corresponding DC problems. These results are based on the Polyak-Łojasiewicz-Kurdyka (PLK) property and the specific PLK exponent assumed on the DME-based model or the potential function designed in the DME-specific algorithm. More importantly, we establish the equivalence of the PLK exponent between the DC problems and their DME-based models. Combined with our local convergence rate result, we are allowed to show the linear and sublinear convergence rates of these specific algorithms. Moreover, the equivalence result also provides a new tool to explore the PLK exponent of the DC problem from that of its DME-based model. An example is then provided to show that the PLK exponent of a nonconvex compressed sensing model that incorporates a logistic penalty term is 1/2, which was previously unknown.

Keywords: Difference-of-Moreau-Envelope smoothing; Polyak-Łojasiewicz-Kurdyka exponent; Difference-of-Convex problems; Inexact gradient descent algorithm; Convergence rate; 90C25; 90C26; 90C90; 68Q25 (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-025-02877-0 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_s10957-025-02877-0

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

DOI: 10.1007/s10957-025-02877-0

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 ().