Abstract
We consider the classical sparse estimation problem of recovering a synthetic sparse signal x0 given measurement vector y=Φx0+w. We propose a tree search algorithm, TSN, driven by a deep neural network for sparse estimation. TSN improves the signal reconstruction performance of the deep neural network designed for sparse estimation by performing a tree search with pruning. In both noiseless and noisy cases, the proposed TSN recovers all synthetic signals at lower complexity than conventional tree search and outperforms existing algorithms by a large margin regarding several variations of sensing matrix Φ, which is widely used in sparse estimation. We also demonstrate the superiority of TSN for two typical applications of sparse estimation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have