Efficient Decentralized Nonlinear Approximation Via Selective Gossip
Recently, gossip algorithms have received much attention from the wireless sensor network community due to their simplicity, scalability and robustness. Motivated by applications such as compression and distributed transform coding, the authors propose a new gossip algorithm called Selective Gossip. Unlike the traditional randomized gossip which computes the average of scalar values, they run gossip algorithms in parallel on the elements of a vector. The goal is to compute only the entries which are above a defined threshold in magnitude, i.e., significant entries. Nodes adaptively approximate the significant entries while abstaining from calculating the insignificant ones. Consequently, network lifetime and bandwidth are preserved.