Multilevel Regularized Newton Methods with Fast Convergence Rates
SIAM Journal on Scientific Computing · 31.10.2026 · 48 (5) · S232-S257
DOI: 10.1137/24m1677307 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 13.08.2025. Verfasst von Nick Tsipinakis und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Gefördert von: Google Cloud Research Award, Nvidia, Engineering and Physical Sciences Research Council.
Abstract (Originalsprache)
We introduce new multilevel methods for solving large-scale unconstrained optimization problems. Specifically, the philosophy of multilevel methods is applied to Newton-type methods that regularize the Newton subproblem using second-order information from a coarse (low dimensional) subproblem. The new regularized multilevel methods provably converge from any initialization point and enjoy faster convergence rates than gradient descent. In particular, for arbitrary functions with Lipschitz continuous Hessians, we show that their convergence rate interpolates between the rate of gradient descent and that of the cubic Newton method. If, additionally, the objective function is assumed to be convex, then the proposed method converges with the fast [Formula: see text] rate. Hence, since the updates are generated using a coarse model in low dimensions, the theoretical results of this paper significantly speed up the convergence of Newton-type or preconditioned gradient methods in practical applications. Preliminary numerical results suggest that the proposed multilevel algorithms are significantly faster than current state-of-the-art methods.
Förderung
- Google Cloud Research Award
- Nvidia
- Engineering and Physical Sciences Research Council
Zitieren
APA
Tsipinakis, N., & Parpas, P. (2026). Multilevel Regularized Newton Methods with Fast Convergence Rates. SIAM Journal on Scientific Computing, 48(5), S232-S257. https://doi.org/10.1137/24m1677307
Vancouver
Tsipinakis N, Parpas P. Multilevel Regularized Newton Methods with Fast Convergence Rates. SIAM Journal on Scientific Computing. 2026;48(5):S232-S257. doi:10.1137/24m1677307
BibTeX
@article{Tsipinakis2026,
author = {Tsipinakis, Nick and Parpas, Panos},
title = {Multilevel Regularized Newton Methods with Fast Convergence Rates},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {5},
pages = {S232--S257},
doi = {10.1137/24m1677307}
}
EUVIMED