Distributed Zero-Order Algorithms for Nonconvex Multiagent Optimization

Distributed multi-agent optimization finds many applications in distributed learning, control, estimation, etc. Most existing algorithms assume knowledge of first-order information the objective and have been analyzed for convex problems. However, there are situations where is nonconvex, one can only evaluate function values at finitely points. In this paper we consider derivative-free nonconvex optimization, based on recent progress zero-order optimization. We develop two different settings, provide detailed analysis their convergence behavior, compare them with centralized gradient-based algorithms.