Ensuring Both Almost Sure Convergence and Differential Privacy in Nash Equilibrium Seeking on Directed Graphs
Yongqiang Wang, Tamer Başar · IEEE Transactions on Automatic Control · 2024
We propose a distributed Nash equilibrium seeking approach that can achieve both almost sure convergence and rigorous differential privacy with finite cumulative privacy budget, which is in sharp contrast to existing differential-privacy solutions for networked games that have to trade provable convergence for differential privacy. The approach is applicable when the communication graph is directed and unbalanced. Numerical comparison results with existing counterparts confirm the effectiveness of the proposed approach.