Saved in:
Bibliographic Details
Main Authors: Hu, Jiang, Deng, Kangkang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.08904
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917720161779712
author Hu, Jiang
Deng, Kangkang
author_facet Hu, Jiang
Deng, Kangkang
contents We are concerned with decentralized optimization over a compact submanifold, where the loss functions of local datasets are defined by their respective local datasets. A key challenge in decentralized optimization is mitigating the communication bottleneck, which primarily involves two strategies: achieving consensus and applying communication compression. Existing projection/retraction-type algorithms rely on multi-step consensus to attain both consensus and optimality. Due to the nonconvex nature of the manifold constraint, it remains an open question whether the requirement for multi-step consensus can be reduced to single-step consensus. We address this question by carefully elaborating on the smoothness structure and the asymptotic 1-Lipschitz continuity associated with the manifold constraint. Furthermore, we integrate these insights with a communication compression strategy to propose a communication-efficient gradient algorithm for decentralized manifold optimization problems, significantly reducing per-iteration communication costs. Additionally, we establish an iteration complexity of $\mathcal{O}(ε^{-1})$ to find an $ε$-stationary point, which matches the complexity in the Euclidean setting. Numerical experiments demonstrate the efficiency of the proposed method in comparison to state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08904
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving the communication in decentralized manifold optimization through single-step consensus and compression
Hu, Jiang
Deng, Kangkang
Optimization and Control
We are concerned with decentralized optimization over a compact submanifold, where the loss functions of local datasets are defined by their respective local datasets. A key challenge in decentralized optimization is mitigating the communication bottleneck, which primarily involves two strategies: achieving consensus and applying communication compression. Existing projection/retraction-type algorithms rely on multi-step consensus to attain both consensus and optimality. Due to the nonconvex nature of the manifold constraint, it remains an open question whether the requirement for multi-step consensus can be reduced to single-step consensus. We address this question by carefully elaborating on the smoothness structure and the asymptotic 1-Lipschitz continuity associated with the manifold constraint. Furthermore, we integrate these insights with a communication compression strategy to propose a communication-efficient gradient algorithm for decentralized manifold optimization problems, significantly reducing per-iteration communication costs. Additionally, we establish an iteration complexity of $\mathcal{O}(ε^{-1})$ to find an $ε$-stationary point, which matches the complexity in the Euclidean setting. Numerical experiments demonstrate the efficiency of the proposed method in comparison to state-of-the-art approaches.
title Improving the communication in decentralized manifold optimization through single-step consensus and compression
topic Optimization and Control
url https://arxiv.org/abs/2407.08904