Approximate Message Passing Algorithm with Universal Denoising and Gaussian Mixture Learning

Abstract

We study compressed sensing (CS) signal reconstruction problems where an input signal is measured via matrix multiplication under additive white Gaussian noise. Our signals are assumed to be stationary and ergodic, but the input statistics are unknown; the goal is to provide reconstruction algorithms that are universal to the input statistics. We present a novel algorithmic framework that combines: (i) the approximate message passing (AMP) CS reconstruction framework, which solves the matrix channel recovery problem by iterative scalar channel denoising; (ii) a universal denoising scheme based on context quantization, which partitions the stationary ergodic signal denoising into independent and identically distributed (i.i.d.) subsequence denoising; and (iii) a density estimation approach that approximates the probability distribution of an i.i.d. sequence by fitting a Gaussian mixture (GM) model. In addition to the algorithmic framework, we provide three contributions: (i) numerical results showing that state evolution holds for non-separable Bayesian sliding-window denoisers; (ii) an i.i.d. denoiser based on a modified GM learning algorithm; and (iii) a universal denoiser that does not need information about the range where the input takes values from or require the input signal to be bounded. We provide two implementations of our universal CS recovery algorithm with one being faster and the other being more accurate. The two implementations compare favorably with existing universal reconstruction algorithms in terms of both reconstruction quality and runtime.

To appear in IEEE Transaction on Signal Processing

References in corpus (4)

• Compressive Imaging via Approximate Message Passing with Image Denoising
• Sparse Estimation with the Swept Approximated Message-Passing Algorithm
• Approximate Message Passing Algorithm with Universal Denoising and Gaussian Mixture Learning
• Information Complexity and Estimation

Cited by in corpus (12)

• Approximate Message Passing Algorithm with Universal Denoising and Gaussian Mixture Learning
• Approximate Message Passing with Parameter Estimation for Heavily Quantized Measurements
• Multi-Processor Approximate Message Passing Using Lossy Compression
• Capacity Optimality of AMP in Coded Systems
• Statistical Physics and Information Theory Perspectives on Linear Inverse Problems
• Optimal Trade-offs in Multi-Processor Approximate Message Passing
• A Probabilistic Bayesian Approach to Recover $R_2^{\ast }$ map and Phase Images for Quantitative Susceptibility Mapping
• An Overview of Multi-Processor Approximate Message Passing
• Analysis of Approximate Message Passing with a Class of Non-Separable Denoisers
• Bayesian Convolutional Neural Networks for Compressed Sensing Restoration
• Analysis of Approximate Message Passing with Non-Separable Denoisers and Markov Random Field Priors
• Nonlinear Function Estimation with Empirical Bayes and Approximate Message Passing