Distributed second order methods with increasing number of working nodes

From MaRDI portal



Abstract: Recently, an idling mechanism has been introduced in the context of distributed emph{first order} methods for minimization of a sum of nodes' local convex costs over a generic, connected network. With the idling mechanism, each node i, at each iteration k, is active -- updates its solution estimate and exchanges messages with its network neighborhood -- with probability pk, and it stays idle with probability 1−pk, while the activations are independent both across nodes and across iterations. In this paper, we demonstrate that the idling mechanism can be successfully incorporated in emph{distributed second order methods} also. Specifically, we apply the idling mechanism to the recently proposed Distributed Quasi Newton method (DQN). We first show theoretically that, when pk grows to one across iterations in a controlled manner, DQN with idling exhibits very similar theoretical convergence and convergence rates properties as the standard DQN method, thus achieving the same order of convergence rate (R-linear) as the standard DQN, but with significantly cheaper updates. Simulation examples confirm the benefits of incorporating the idling mechanism, demonstrate the method's flexibility with respect to the choice of the pk's, and compare the proposed idling method with related algorithms from the literature.














This page was built for publication: Distributed second order methods with increasing number of working nodes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6290889)