Optimization over time-varying networks with unbounded delays (1912.07055v2)

Abstract: Solving optimization problems in multi-agent systems (MAS) involves information exchange between agents. These solutions must be robust to delays and errors that arise from an unreliable wireless network which typically connects the MAS. In today's large-scale dynamic Internet Of Things style multi-agent scenarios, the network topology changes and evolves over time. In this paper, we present a simple distributed gradient based optimization framework and an associated algorithm. Convergence to a minimum of a given objective is shown under mild conditions on the network topology and objective. Specifically, we only assume that a message sent by a sender reaches the intended receiver, possibly delayed, with some positive probability. To the best of our knowledge ours is the first analysis under such weak general network conditions. We also discuss in detail the verifiability of all assumptions involved. This paper makes a significant technical contribution in terms of the allowed class of objective functions. Specifically, we present an analysis wherein the objective function is such that its sample-gradient is merely locally Lipschitz continuous. The theory developed herein is supported by numerical results. Another contribution of this paper is a consensus algorithm based on the main framework/ algorithm. The long-term behavior of this consensus algorithm is a direct consequence of the theory presented. Again, we believe that ours is the first consensus algorithm to account for unbounded stochastic communication delays, in addition to time-varying networks.