Last-Iterate Convergence of Anchored Gradient Descent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Yang, Zheng, Weiqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918445757497344
author Cai, Yang
Zheng, Weiqiang
author_facet Cai, Yang
Zheng, Weiqiang
contents We study the monotone inclusion problem $0\in F(z)+A(z)$, where $F$ is monotone and Lipschitz, and $A$ is maximally monotone, a framework that encompasses monotone variational inequalities and convex-concave saddle-point problems with constraints or regularization. It is well known that vanilla gradient descent diverges for this problem, whereas optimism-based methods such as Extragradient and accelerated methods that combine both optimism and anchoring, such as Extra Anchored Gradient, achieve last-iterate convergence. However, the anchoring-only method, anchored gradient descent, has been studied only in the unconstrained setting [RYY19, SST+26]. In this note, we extend the anchored gradient descent method to the monotone inclusion problem and prove a last-iterate convergence rate of $O(1/\sqrt{T})$ in terms of the tangent residual. We build on the recent proof in the unconstrained setting [SST+26] and use techniques from [COZ24] to extend it to the general inclusion setting.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12235
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Last-Iterate Convergence of Anchored Gradient Descent
Cai, Yang
Zheng, Weiqiang
Optimization and Control
We study the monotone inclusion problem $0\in F(z)+A(z)$, where $F$ is monotone and Lipschitz, and $A$ is maximally monotone, a framework that encompasses monotone variational inequalities and convex-concave saddle-point problems with constraints or regularization. It is well known that vanilla gradient descent diverges for this problem, whereas optimism-based methods such as Extragradient and accelerated methods that combine both optimism and anchoring, such as Extra Anchored Gradient, achieve last-iterate convergence. However, the anchoring-only method, anchored gradient descent, has been studied only in the unconstrained setting [RYY19, SST+26]. In this note, we extend the anchored gradient descent method to the monotone inclusion problem and prove a last-iterate convergence rate of $O(1/\sqrt{T})$ in terms of the tangent residual. We build on the recent proof in the unconstrained setting [SST+26] and use techniques from [COZ24] to extend it to the general inclusion setting.
title Last-Iterate Convergence of Anchored Gradient Descent
topic Optimization and Control
url https://arxiv.org/abs/2604.12235