Calculus rules of the generalized concave Kurdyka-\L ojasiewicz property
Xianfu Wang, Ziyuan Wang

TL;DR
This paper develops new calculus rules for the generalized concave Kurdyka-ojasiewicz property, broadening applicability by removing assumptions on the form and differentiability of desingularizing functions, with implications for optimization theory.
Contribution
It introduces generalized calculus rules for the KL property that do not require specific forms or differentiability of desingularizing functions, extending previous results.
Findings
Rules applicable to broader class of functions
Applicable to nondifferentiable desingularizing functions
Enhances theoretical understanding of KL property
Abstract
In this paper, we propose several calculus rules for the generalized concave Kurdyka-\L ojasiewicz (KL) property, which generalize Li and Pong's results for KL exponents. The optimal concave desingularizing function has various forms and may be nondifferentiable. Our calculus rules do not assume desingularizing functions to have any specific form nor differentiable, while the known results do. Several examples are also given to show that our calculus rules are applicable to a broader class of functions than the known ones.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
