Saved in:
Bibliographic Details
Main Authors: Zhang, Wentao, Shi, Yang, Zhang, Baoyong, Yuan, Deming
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.12957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917693754441728
author Zhang, Wentao
Shi, Yang
Zhang, Baoyong
Yuan, Deming
author_facet Zhang, Wentao
Shi, Yang
Zhang, Baoyong
Yuan, Deming
contents In this paper, we consider a distributed online convex optimization problem over a time-varying multi-agent network. The goal of this network is to minimize a global loss function through local computation and communication with neighbors. To effectively handle the optimization problem with a high-dimensional and structural constraint set, we develop a distributed online multiple Frank-Wolfe algorithm to avoid the expensive computational cost of projection operation. The dynamic regret bounds are established as $\mathcal{O}(T^{1-γ}+H_T)$ with the linear oracle number $\mathcal{O} (T^{1+γ})$, which depends on the horizon (total iteration number) $T$, the function variation $H_T$, and the tuning parameter $0<γ<1$. In particular, when the prior knowledge of $H_T$ and $T$ is available, the bound can be enhanced to $\mathcal{O} (1+H_T)$. Moreover, we illustrate the significant advantages of the multiple iteration technique and reveal a trade-off between dynamic regret bound, computational cost, and communication cost. Finally, the performance of our algorithm is verified and compared through the distributed online ridge regression problems with two constraint sets.
format Preprint
id arxiv_https___arxiv_org_abs_2305_12957
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improved Dynamic Regret of Distributed Online Multiple Frank-Wolfe Convex Optimization
Zhang, Wentao
Shi, Yang
Zhang, Baoyong
Yuan, Deming
Optimization and Control
In this paper, we consider a distributed online convex optimization problem over a time-varying multi-agent network. The goal of this network is to minimize a global loss function through local computation and communication with neighbors. To effectively handle the optimization problem with a high-dimensional and structural constraint set, we develop a distributed online multiple Frank-Wolfe algorithm to avoid the expensive computational cost of projection operation. The dynamic regret bounds are established as $\mathcal{O}(T^{1-γ}+H_T)$ with the linear oracle number $\mathcal{O} (T^{1+γ})$, which depends on the horizon (total iteration number) $T$, the function variation $H_T$, and the tuning parameter $0<γ<1$. In particular, when the prior knowledge of $H_T$ and $T$ is available, the bound can be enhanced to $\mathcal{O} (1+H_T)$. Moreover, we illustrate the significant advantages of the multiple iteration technique and reveal a trade-off between dynamic regret bound, computational cost, and communication cost. Finally, the performance of our algorithm is verified and compared through the distributed online ridge regression problems with two constraint sets.
title Improved Dynamic Regret of Distributed Online Multiple Frank-Wolfe Convex Optimization
topic Optimization and Control
url https://arxiv.org/abs/2305.12957