Kurdyka–Łojasiewicz Exponent via Hadamard Parametrization
SIAM Journal on Optimization · 31.03.2025 · 35 (1) · 62-91
DOI: 10.1137/24m1636186 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 03.01.2025. Verfasst von Wenqing Ouyang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Natural Science Foundation of Sichuan Province, Southwest Minzu University Research Funds, Natural Science Foundation of Shanghai Municipality.
Abstract (Originalsprache)
We consider a class of [Formula: see text]-regularized optimization problems and the associated smooth “overparameterized” optimization problems built upon the Hadamard parametrization, or equivalently, the Hadamard difference parametrization (HDP). We characterize the set of second-order stationary points of the HDP-based model and show that they correspond to some stationary points of the corresponding [Formula: see text]-regularized model. More importantly, we show that the Kurdyka–Łojasiewicz (KL) exponent of the HDP-based model at a second-order stationary point can be inferred from that of the corresponding [Formula: see text]-regularized model under suitable assumptions. Our assumptions are general enough to cover a wide variety of loss functions commonly used in [Formula: see text]-regularized models, such as the least squares loss function and the logistic loss function. Since the KL exponents of many [Formula: see text]-regularized models are explicitly known in the literature, our results allow us to leverage these known exponents to deduce the KL exponents at second-order stationary points of the corresponding HDP-based models, which were previously unknown. Finally, we demonstrate how these explicit KL exponents at second-order stationary points can be applied to deducing the explicit local convergence rate of a standard gradient descent method for minimizing the HDP-based model.
Förderung
- Natural Science Foundation of Sichuan Province
- Southwest Minzu University Research Funds
- Natural Science Foundation of Shanghai Municipality
- Research Grants Council, University Grants Committee
Zitieren
APA
Ouyang, W., Liu, Y., Pong, T. K., & Wang, H. (2025). Kurdyka–Łojasiewicz Exponent via Hadamard Parametrization. SIAM Journal on Optimization, 35(1), 62-91. https://doi.org/10.1137/24m1636186
Vancouver
Ouyang W, Liu Y, Pong TK, Wang H. Kurdyka–Łojasiewicz Exponent via Hadamard Parametrization. SIAM Journal on Optimization. 2025;35(1):62-91. doi:10.1137/24m1636186
BibTeX
@article{Ouyang2025,
author = {Ouyang, Wenqing and Liu, Yuncheng and Pong, Ting Kei and Wang, Hao},
title = {Kurdyka–Łojasiewicz Exponent via Hadamard Parametrization},
journal = {SIAM Journal on Optimization},
year = {2025},
volume = {35},
number = {1},
pages = {62--91},
doi = {10.1137/24m1636186}
}
EUVIMED