Accelerated Gossip via Stochastic Heavy Ball Method
This work addresses distributed averaging for wireless sensor networks, presenting an incremental improvement by adapting existing optimization methods to gossip protocols.
The paper tackles the average consensus problem in distributed networks by interpreting the stochastic heavy ball method as a randomized gossip algorithm, resulting in protocols where all nodes update values but only a subset exchanges private data, with numerical experiments on wireless sensor networks showing benefits.
In this paper we show how the stochastic heavy ball method (SHB) -- a popular method for solving stochastic convex and non-convex optimization problems --operates as a randomized gossip algorithm. In particular, we focus on two special cases of SHB: the Randomized Kaczmarz method with momentum and its block variant. Building upon a recent framework for the design and analysis of randomized gossip algorithms, [Loizou Richtarik, 2016] we interpret the distributed nature of the proposed methods. We present novel protocols for solving the average consensus problem where in each step all nodes of the network update their values but only a subset of them exchange their private values. Numerical experiments on popular wireless sensor networks showing the benefits of our protocols are also presented.