Gradient-tracking based Distributed Optimization with Guaranteed Optimality under Noisy Information Sharing

TL;DR

This paper introduces a gradient-tracking distributed optimization method that guarantees convergence to the optimal solution despite persistent noisy information sharing, applicable to time-varying directed networks and noisy gradients.

Contribution

It proposes a novel gradient-tracking algorithm that prevents noise accumulation and ensures almost sure convergence under persistent noise and time-varying network conditions.

Findings

Ensures convergence despite persistent sharing noise.

Applicable to directed, time-varying networks.

Handles noisy gradients in machine learning contexts.

Abstract

Distributed optimization enables networked agents to cooperatively solve a global optimization problem even with each participating agent only having access to a local partial view of the objective function. 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 paper 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 {inter-agent interaction is} time-varying, which is key to enable the incorporation of a decaying factor in inter-agent 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.