Parameter-Free Accelerated Gradient Descent for Nonconvex Minimization
SIAM Journal on Optimization · 30.06.2024 · 34 (2) · 2093-2120
DOI: 10.1137/22m1540934 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 17.06.2024. Verfasst von Naoki Marumo und 1 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: JSPS KAKENHI, JST ERATO.
Abstract (Originalsprache)
We propose a new first-order method for minimizing nonconvex functions with a Lipschitz continuous gradient and Hessian. The proposed method is an accelerated gradient descent with two restart mechanisms and finds a solution where the gradient norm is less than [Formula: see text] in [Formula: see text] function and gradient evaluations. Unlike existing first-order methods with similar complexity bounds, our algorithm is parameter-free because it requires no prior knowledge of problem-dependent parameters, e.g., the Lipschitz constants and the target accuracy [Formula: see text]. The main challenge in achieving this advantage is estimating the Lipschitz constant of the Hessian using only first-order information. To this end, we develop a new Hessian-free analysis based on two technical inequalities: a Jensen-type inequality for gradients and an error bound for the trapezoidal rule. Several numerical results illustrate that the proposed method performs comparably to existing algorithms with similar complexity bounds, even without parameter tuning.
Förderung
- JSPS KAKENHI
- JST ERATO
Zitieren
APA
Marumo, N., & Takeda, A. (2024). Parameter-Free Accelerated Gradient Descent for Nonconvex Minimization. SIAM Journal on Optimization, 34(2), 2093-2120. https://doi.org/10.1137/22m1540934
Vancouver
Marumo N, Takeda A. Parameter-Free Accelerated Gradient Descent for Nonconvex Minimization. SIAM Journal on Optimization. 2024;34(2):2093-2120. doi:10.1137/22m1540934
BibTeX
@article{Marumo2024,
author = {Marumo, Naoki and Takeda, Akiko},
title = {Parameter-Free Accelerated Gradient Descent for Nonconvex Minimization},
journal = {SIAM Journal on Optimization},
year = {2024},
volume = {34},
number = {2},
pages = {2093--2120},
doi = {10.1137/22m1540934}
}
EUVIMED