Tree Search Network for Sparse Regression

Abstract

We consider the classical sparse regression problem of recovering a sparse signal $x_0$ given a measurement vector $y=\Phi x_0+w$. 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 $\Phi$, widely used in sparse regression.

References in corpus (16)

• Sparse Signal Recovery with Temporally Correlated Source Vectors Using Sparse Bayesian Learning
• Generalized Orthogonal Matching Pursuit
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Gated Feedback Recurrent Neural Networks
• Compressed Sensing using Generative Models
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Distributed Compressive Sensing: A Deep Learning Approach
• Maximal Sparsity with Deep Networks?
• ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
• Approximate Message Passing with Restricted Boltzmann Machine Priors
• From Bayesian Sparsity to Gated Recurrent Nets
• Deep Sparse Coding Using Optimized Linear Expansion of Thresholds
• Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP