Gradient-Tracking-Based Distributed Optimization With Guaranteed Optimality Under Noisy Information Sharing

Yongqiang Wang

doi:10.1109/TAC.2022.3212006

2023-08-01

PRE

Yongqiang Wang *

Tamer Başar

DOI：10.1109/TAC.2022.3212006

原文链接

原文求助

摘要

En 中文

Distributed optimization enables networked agents to cooperatively solve a global optimization problem. Despite making significant inroads, most existing results on distributed optimization rely on noise-free information sharing among the agents, which is problematic when communication channels are noisy, messages are coarsely quantized, or shared information are obscured by additive noise for the purpose of achieving differential privacy. The problem of information-sharing noise is particularly pronounced in the state-of-the-art gradient-tracking-based distributed optimization algorithms, in that information-sharing noise will accumulate with iterations on the gradient-tracking estimate of these algorithms, and the ensuing variance will even grow unbounded when the noise is persistent. This article proposes a new gradient-tracking-based distributed optimization approach that can avoid information-sharing noise from accumulating in the gradient estimation. The approach is applicable even when the interagent interaction is time-varying, which is key to enable the incorporation of a decaying factor in interagent interaction to gradually eliminate the influence of information-sharing noise. In fact, we rigorously prove that the proposed approach can ensure the almost sure convergence of all agents to the same optimal solution even in the presence of persistent information-sharing noise. The approach is applicable to general directed graphs. It is also capable of ensuring the almost sure convergence of all agents to an optimal solution when the gradients are noisy, which is common in machine learning applications. Numerical simulations confirm the effectiveness of the proposed approach.

Keyword:

Distributed optimization

gradient tracking

information-sharing noise

stochastic gradient methods