Saved in:
Bibliographic Details
Main Authors: Wu, Jiayuan, Deng, Zhanwang, Hu, Jiang, Su, Weijie, Wen, Zaiwen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.15537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918029085900800
author Wu, Jiayuan
Deng, Zhanwang
Hu, Jiang
Su, Weijie
Wen, Zaiwen
author_facet Wu, Jiayuan
Deng, Zhanwang
Hu, Jiang
Su, Weijie
Wen, Zaiwen
contents We consider decentralized optimization over a compact Riemannian submanifold in a network of $n$ agents, where each agent holds a smooth, nonconvex local objective defined by its private data. The goal is to collaboratively minimize the sum of these local objective functions. In the presence of data heterogeneity across nodes, existing algorithms typically require communicating both local gradients and iterates to ensure exact convergence with constant step sizes. In this work, we propose REXTRA, a Riemannian extension of the EXTRA algorithm [Shi et al., SIOPT, 2015], to address this limitation. On the theoretical side, we leverage proximal smoothness to overcome the challenges of manifold nonconvexity and establish a global sublinear convergence rate of $\mathcal{O}(1/k)$, matching the best-known results. To our knowledge, REXTRA is the first algorithm to achieve a global sublinear convergence rate under a constant step size while requiring only a single round of local iterate communication per iteration. Numerical experiments show that REXTRA achieves superior performance compared to state-of-the-art methods, while supporting larger step sizes and reducing total communication by over 50\%.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15537
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Riemannian EXTRA: Communication-efficient decentralized optimization over compact submanifolds with data heterogeneity
Wu, Jiayuan
Deng, Zhanwang
Hu, Jiang
Su, Weijie
Wen, Zaiwen
Optimization and Control
We consider decentralized optimization over a compact Riemannian submanifold in a network of $n$ agents, where each agent holds a smooth, nonconvex local objective defined by its private data. The goal is to collaboratively minimize the sum of these local objective functions. In the presence of data heterogeneity across nodes, existing algorithms typically require communicating both local gradients and iterates to ensure exact convergence with constant step sizes. In this work, we propose REXTRA, a Riemannian extension of the EXTRA algorithm [Shi et al., SIOPT, 2015], to address this limitation. On the theoretical side, we leverage proximal smoothness to overcome the challenges of manifold nonconvexity and establish a global sublinear convergence rate of $\mathcal{O}(1/k)$, matching the best-known results. To our knowledge, REXTRA is the first algorithm to achieve a global sublinear convergence rate under a constant step size while requiring only a single round of local iterate communication per iteration. Numerical experiments show that REXTRA achieves superior performance compared to state-of-the-art methods, while supporting larger step sizes and reducing total communication by over 50\%.
title Riemannian EXTRA: Communication-efficient decentralized optimization over compact submanifolds with data heterogeneity
topic Optimization and Control
url https://arxiv.org/abs/2505.15537