A semi-Bregman proximal alternating method for a class of nonconvex problems: local and global convergence analysis

Eyal Cohen, D. Russell Luke, Titus Pinta, Shoham Sabach*, Marc Teboulle

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We focus on nonconvex and non-smooth block optimization problems, where the smooth coupling part of the objective does not satisfy a global/partial Lipschitz gradient continuity assumption. A general alternating minimization algorithm is proposed that combines two proximal-based steps, one classical and another with respect to the Bregman divergence. Combining different analytical techniques, we provide a complete analysis of the behavior—from global to local—of the algorithm, and show when the iterates converge globally to critical points with a locally linear rate for sufficiently regular (though not necessarily convex) objectives. Numerical experiments illustrate the theoretical findings.

Original languageEnglish
Pages (from-to)33-55
Number of pages23
JournalJournal of Global Optimization
Volume89
Issue number1
DOIs
StatePublished - May 2024

Funding

FundersFunder number
Deutsche Forschungsgemeinschaft—LU 170211-1
Israel Science Foundation2619-20, 2480-21

    Keywords

    • 49M20
    • 65K05
    • 65K10
    • 90C26
    • Alternating minimization
    • Bregman proximal splitting
    • Nonconvex and non-smooth minimization
    • Primary 49J52
    • Quadratic optimization
    • Secondary 47H09

    Fingerprint

    Dive into the research topics of 'A semi-Bregman proximal alternating method for a class of nonconvex problems: local and global convergence analysis'. Together they form a unique fingerprint.

    Cite this