Adaptive Bayesian Estimation with Cluster Structured Sparsity

Abstract

Armed with structures, group sparsity can be exploited to extraordinarily improve the performance of adaptive estimation. In this letter, the adaptive estimation algorithm for cluster structured sparse signals, called A-CluSS, is proposed. In particular, a hierarchical Bayesian model is built, where both sparse prior and cluster structured prior are exploited simultaneously. The adaptive updating formulas for statistical variables are obtained via the variational Bayesian inference and the resulted algorithms can adaptively estimate the cluster structured sparse signals without knowledge of block size, block numbers and block locations. Superiority of proposed A-CluSS is demonstrated via various simulations.