Tree Search Network for Sparse Regression
This work addresses sparse signal recovery for applications like compressed sensing, but it appears incremental as it builds on existing deep neural network methods with tree search improvements.
The paper tackles the sparse regression problem by proposing a tree search network (TSN) that enhances signal reconstruction performance through tree search with pruning, achieving superior results over existing algorithms for various sensing matrices.
We consider the classical sparse regression problem of recovering a sparse signal $x_0$ given a measurement vector $y = Φx_0+w$. We propose a tree search algorithm driven by the deep neural network for sparse regression (TSN). TSN improves the signal reconstruction performance of the deep neural network designed for sparse regression by performing a tree search with pruning. It is observed in both noiseless and noisy cases, TSN recovers synthetic and real signals with lower complexity than a conventional tree search and is superior to existing algorithms by a large margin for various types of the sensing matrix $Φ$, widely used in sparse regression.