English

Last-Iterate Convergence of Anchored Gradient Descent

Optimization and Control 2026-04-15 v1

Abstract

We study the monotone inclusion problem 0F(z)+A(z)0\in F(z)+A(z), where FF is monotone and Lipschitz, and AA 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/T)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.

Keywords

Cite

@article{arxiv.2604.12235,
  title  = {Last-Iterate Convergence of Anchored Gradient Descent},
  author = {Yang Cai and Weiqiang Zheng},
  journal= {arXiv preprint arXiv:2604.12235},
  year   = {2026}
}