Loopless Proximal Riemannian Gradient EXTRA for Distributed Optimization on Compact Manifolds

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiong, Yongyang, Ouyang, Chen, You, Keyou, Shi, Yang, Wu, Ligang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910046375378944
author Xiong, Yongyang
Ouyang, Chen
You, Keyou
Shi, Yang
Wu, Ligang
author_facet Xiong, Yongyang
Ouyang, Chen
You, Keyou
Shi, Yang
Wu, Ligang
contents Distributed optimization has gained substantial interest in recent years due to its wide applications in machine learning. However, most of existing algorithms are designed for Euclidean spaces, leaving composite optimization on Riemannian manifolds largely unexplored. To bridge this gap, we propose the proximal Riemannian gradient EXTRA algorithm (PR-EXTRA) to solve distributed composite optimization problem with nonsmooth regularizer over compact manifolds. In each iteration, PR-EXTRA requires only a single round communication, coupled with local gradient evaluations and proximal mappings. Furthermore, a manifold projection operator is integrated to ensure the feasibility of all iterates throughout the optimization process. Theoretical analysis shows that with a constant stepsize, PR-EXTRA achieves a sublinear convergence rate of $\mathcal{O}(1/K)$ to a stationary point, matching the proximal gradient EXTRA algorithm in Euclidean spaces. Numerical experiments show the effectiveness of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08367
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Loopless Proximal Riemannian Gradient EXTRA for Distributed Optimization on Compact Manifolds
Xiong, Yongyang
Ouyang, Chen
You, Keyou
Shi, Yang
Wu, Ligang
Optimization and Control
Distributed optimization has gained substantial interest in recent years due to its wide applications in machine learning. However, most of existing algorithms are designed for Euclidean spaces, leaving composite optimization on Riemannian manifolds largely unexplored. To bridge this gap, we propose the proximal Riemannian gradient EXTRA algorithm (PR-EXTRA) to solve distributed composite optimization problem with nonsmooth regularizer over compact manifolds. In each iteration, PR-EXTRA requires only a single round communication, coupled with local gradient evaluations and proximal mappings. Furthermore, a manifold projection operator is integrated to ensure the feasibility of all iterates throughout the optimization process. Theoretical analysis shows that with a constant stepsize, PR-EXTRA achieves a sublinear convergence rate of $\mathcal{O}(1/K)$ to a stationary point, matching the proximal gradient EXTRA algorithm in Euclidean spaces. Numerical experiments show the effectiveness of the proposed algorithm.
title Loopless Proximal Riemannian Gradient EXTRA for Distributed Optimization on Compact Manifolds
topic Optimization and Control
url https://arxiv.org/abs/2603.08367