Nesterov Acceleration with Operator Decomposition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Jaewook, Ryu, Ernest K., Yun, Chulhee
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908959740264448
author Lee, Jaewook
Ryu, Ernest K.
Yun, Chulhee
author_facet Lee, Jaewook
Ryu, Ernest K.
Yun, Chulhee
contents We propose Nesterov acceleration with Operator Decomposition (NOD), which extends Nesterov's accelerated gradient descent (NAG) from smooth strongly convex optimization to the broader setting of strongly monotone, Lipschitz operators. The key insight is to decompose the operator into cyclically monotone and monotone components, with the Asplund decomposition providing the tightest such representation, and to have the algorithm utilize the decomposed oracles. NOD and its analysis subsume the classical theory of Nesterov acceleration and yield an iteration complexity for finding an $ε$-accurate solution of \[ Θ\left(\sqrt{\frac{L_ϕ}μ + \frac{L_{\mathbb{S}}^2}{μ^2}} \,\log \frac{1}ε\right), \] where $μ$ is the strong monotonicity parameter, $L_ϕ$ is the Lipschitz constant of the cyclically monotone component, and $L_{\mathbb{S}}$ is the Lipschitz constant of the (possibly acyclic) monotone remainder.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11105
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Nesterov Acceleration with Operator Decomposition
Lee, Jaewook
Ryu, Ernest K.
Yun, Chulhee
Optimization and Control
We propose Nesterov acceleration with Operator Decomposition (NOD), which extends Nesterov's accelerated gradient descent (NAG) from smooth strongly convex optimization to the broader setting of strongly monotone, Lipschitz operators. The key insight is to decompose the operator into cyclically monotone and monotone components, with the Asplund decomposition providing the tightest such representation, and to have the algorithm utilize the decomposed oracles. NOD and its analysis subsume the classical theory of Nesterov acceleration and yield an iteration complexity for finding an $ε$-accurate solution of \[ Θ\left(\sqrt{\frac{L_ϕ}μ + \frac{L_{\mathbb{S}}^2}{μ^2}} \,\log \frac{1}ε\right), \] where $μ$ is the strong monotonicity parameter, $L_ϕ$ is the Lipschitz constant of the cyclically monotone component, and $L_{\mathbb{S}}$ is the Lipschitz constant of the (possibly acyclic) monotone remainder.
title Nesterov Acceleration with Operator Decomposition
topic Optimization and Control
url https://arxiv.org/abs/2604.11105