Decentralized Nonconvex Robust Optimization over Unsafe Multiagent Systems: System Modeling, Utility, Resilience, and Privacy Analysis

TL;DR

This paper introduces a decentralized algorithm for nonconvex multi-agent optimization that ensures privacy, resilience against Byzantine failures, and convergence, addressing critical issues in secure and robust multi-agent decision-making.

Contribution

It proposes the DP-SCC-PL algorithm combining differential privacy and Byzantine resilience for nonconvex optimization under the P-{ extL}ojasiewicz condition, with convergence analysis and practical validation.

Findings

Achieves consensus among reliable agents.

Ensures differential privacy and Byzantine resilience.

Demonstrates sublinear convergence in experiments.

Abstract

Privacy leakage and Byzantine failures are two adverse factors to the intelligent decision-making process of multi-agent systems (MASs). Considering the presence of these two issues, this paper targets the resolution of a class of nonconvex optimization problems under the Polyak-{\L}ojasiewicz (P-{\L}) condition. To address this problem, we first identify and construct the adversary system model. To enhance the robustness of stochastic gradient descent methods, we mask the local gradients with Gaussian noises and adopt a resilient aggregation method self-centered clipping (SCC) to design a differentially private (DP) decentralized Byzantine-resilient algorithm, namely DP-SCC-PL, which simultaneously achieves differential privacy and Byzantine resilience. The convergence analysis of DP-SCC-PL is challenging since the convergence error can be contributed jointly by privacy-preserving and Byzantine-resilient mechanisms, as well as the nonconvex relaxation, which is addressed via seeking the contraction relationships among the disagreement measure of reliable agents before and after aggregation, together with the optimal gap. Theoretical results reveal that DP-SCC-PL achieves consensus among all reliable agents and sublinear (inexact) convergence with well-designed step-sizes. It has also been proved that if there are no privacy issues and Byzantine agents, then the asymptotic exact convergence can be recovered. Numerical experiments verify the utility, resilience, and differential privacy of DP-SCC-PL by tackling a nonconvex optimization problem satisfying the P-{\L} condition under various Byzantine attacks.