SyncAI.news, a Varaisys broadcasting
Retraction-Based Gradient Projection Algorithms on Manifolds
CX

Conglong Xu, Hao Wu

· 1 min read

ResearcharXiv cs.LG

Retraction-Based Gradient Projection Algorithms on Manifolds

arXiv:2609.30885v1 Announce Type: cross Abstract: We introduce a framework for retraction-based convex optimization on Riemannian manifolds, which includes a notion of retraction-specific convex sets and retraction-based gradient projection algorithms. The standard theory of gradient projection algorithms generalizes easily to this framework. Within this framework, we establish convergence results for retraction-based gradient projection algorithms with various stepsize rules. As an application, we use our framework to study the weighted low-rank approximation. We also provide numerical validation of our convergence results on the image completion task.

Original source

This story was published by arXiv cs.LG and written by Conglong Xu, Hao Wu. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News