Error Bound and Isocost Imply Linear Convergence of DCA-Based Algorithms to D-Stationarity

Min Tao () and Jiang-Ning Li ()
Additional contact information
Min Tao: Nanjing University
Jiang-Ning Li: Nanjing University

Journal of Optimization Theory and Applications, 2023, vol. 197, issue 1, No 8, 205-232

Abstract: Abstract We consider a class of structured nonsmooth difference-of-convex minimization, which can be written as the difference of two convex functions possibly nonsmooth with the second one in the format of the maximum of a finite convex smooth functions. We propose two extrapolation proximal difference-of-convex-based algorithms for potential acceleration to converge to a weak/standard d-stationary point of the structured nonsmooth problem, and prove its linear convergence of these algorithms under the assumptions of piecewise error bound and piecewise isocost condition. As a product, we refine the linear convergence analysis of sDCA and $$\varepsilon $$ ε -DCA in a recent work of Dong and Tao (J Optim Theory Appl 189: 190–220, 2021) by removing the assumption of locally linear regularity regarding the intersection of certain stationary sets and dominance regions. We also discuss sufficient conditions to guarantee these assumptions and illustrate that several sparse learning models satisfy all these assumptions. Finally, we conduct some elementary numerical simulations on sparse recovery to verify the theoretical results empirically.

Keywords: Difference-of-convex programming; Difference-of-convex algorithm; Linear convergence; Error bound; 90C30; 90C26 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-023-02171-x 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:197:y:2023:i:1:d:10.1007_s10957-023-02171-x

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

DOI: 10.1007/s10957-023-02171-x

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 ().