Saved in:
Bibliographic Details
Main Authors: Wu, Yan, Ouyang, Yuyuan, Zhang, Zhe, Luo, Qi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.23492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917501866082304
author Wu, Yan
Ouyang, Yuyuan
Zhang, Zhe
Luo, Qi
author_facet Wu, Yan
Ouyang, Yuyuan
Zhang, Zhe
Luo, Qi
contents We propose a Parameter-Free Universal Gradient Sliding (PFUGS) algorithm for computing an approximate solution to the convex composite optimization $\min_{x\in X} \{f(x) + g(x)\}$, where $f$ has $(M_ν,ν)$-Hölder continuous subgradient and $g$ has $L$-Lipschitz continuous gradient. PFUGS computes an $\varepsilon$-approximate solution with $\mathcal{O}((M_ν/\varepsilon)^{{2}/{(1+3ν)}})$ evaluations of (sub)gradients of $f$ and $\mathcal{O}((L/\varepsilon)^{1/2})$ evaluations of gradients of $g$, without prior knowledge of problem constants. To the best of our knowledge, PFUGS is the first gradient sliding algorithm for problems involving two functions whose distinct problem constants are both unknown a priori.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Universal and Parameter-free Gradient Sliding for Composite Optimization
Wu, Yan
Ouyang, Yuyuan
Zhang, Zhe
Luo, Qi
Optimization and Control
We propose a Parameter-Free Universal Gradient Sliding (PFUGS) algorithm for computing an approximate solution to the convex composite optimization $\min_{x\in X} \{f(x) + g(x)\}$, where $f$ has $(M_ν,ν)$-Hölder continuous subgradient and $g$ has $L$-Lipschitz continuous gradient. PFUGS computes an $\varepsilon$-approximate solution with $\mathcal{O}((M_ν/\varepsilon)^{{2}/{(1+3ν)}})$ evaluations of (sub)gradients of $f$ and $\mathcal{O}((L/\varepsilon)^{1/2})$ evaluations of gradients of $g$, without prior knowledge of problem constants. To the best of our knowledge, PFUGS is the first gradient sliding algorithm for problems involving two functions whose distinct problem constants are both unknown a priori.
title Universal and Parameter-free Gradient Sliding for Composite Optimization
topic Optimization and Control
url https://arxiv.org/abs/2603.23492