Polyak–Łojasiewicz Inequality and Backtracking Line‐search in Iterative Feedback Tuning
IET Control Theory & Applications · 2026-01 · 20 (1)
DOI: 10.1049/cth2.70133 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Control Theory & Applications, online erschienen am 29.06.2026. Verfasst von Mitsuru Toyoda und 1 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
This paper explores the Polyak–Łojasiewicz inequality and presents an associated convergence analysis of the gradient method with the backtracking line‐search in the iterative feedback tuning (IFT). In the conventional IFT, because stepsize design requires the information of a target unknown model, theoretical convergence guarantee is unavailable in practical applications, and the stepsize design has been developed in terms of numerical experiments in existing studies. Even if the aforementioned stepsize, depending on a part of the model information, can be ideally available, convergence rate has hardly been studied. Under some assumptions, this paper derives a PŁ inequality, and the linear convergence is established by exploiting the gradient descent condition using the backtracking line‐search, which leads to an automated stepsize search mechanism with the theoretical convergence guarantee.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Toyoda, M., & Masuda, S. (2026). Polyak–Łojasiewicz Inequality and Backtracking Line‐search in Iterative Feedback Tuning. IET Control Theory & Applications, 20(1). https://doi.org/10.1049/cth2.70133
Vancouver
Toyoda M, Masuda S. Polyak–Łojasiewicz Inequality and Backtracking Line‐search in Iterative Feedback Tuning. IET Control Theory & Applications. 2026;20(1). doi:10.1049/cth2.70133
BibTeX
@article{Toyoda2026,
author = {Toyoda, Mitsuru and Masuda, Shiro},
title = {Polyak–Łojasiewicz Inequality and Backtracking Line‐search in Iterative Feedback Tuning},
journal = {IET Control Theory & Applications},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/cth2.70133}
}
EUVIMED