Privacy Protection of Dual Averaging Push for Decentralized Optimization via Zero-Sum Structured Perturbations

Summary

This study addresses decentralized constrained optimization over time-varying, directed networks, where transmitted information can reveal sensitive data about nodes. The authors propose ZS-DDAPush, which embeds zero-sum structured functional and state perturbations into the decentralized dual averaging push method. The authors state that it protects nodes' cost functions without sacrificing optimization accuracy, and that it converges accurately under weaker initial conditions, with experiments confirming its effectiveness.