Expectation-Maximization Gaussian-Mixture Approximate Message Passing

Abstract

When recovering a sparse signal from noisy compressive linear measurements, the distribution of the signal's non-zero coefficients can have a profound effect on recovery mean-squared error (MSE). If this distribution was apriori known, then one could use computationally efficient approximate message passing (AMP) techniques for nearly minimum MSE (MMSE) recovery. In practice, though, the distribution is unknown, motivating the use of robust algorithms like LASSO---which is nearly minimax optimal---at the cost of significantly larger MSE for non-least-favorable distributions. As an alternative, we propose an empirical-Bayesian technique that simultaneously learns the signal distribution while MMSE-recovering the signal---according to the learned distribution---using AMP. In particular, we model the non-zero distribution as a Gaussian mixture, and learn its parameters through expectation maximization, using AMP to implement the expectation step. Numerical experiments on a wide range of signal classes confirm the state-of-the-art performance of our approach, in both reconstruction error and runtime, in the high-dimensional regime, for most (but not all) sensing operators.

References in corpus (2)

• A fast approach for overcomplete sparse decomposition based on smoothed L0 norm
• Approximate Message Passing with Consistent Parameter Estimation and Applications to Sparse Learning

Cited by in corpus (102)

• Compressed Channel Estimation and Joint Beamforming for Intelligent Reflecting Surface-Assisted Millimeter Wave Systems
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Compressive Sensing Based Adaptive Active User Detection and Channel Estimation: Massive Access Meets Massive MIMO
• Compressed Sensing for Energy-Efficient Wireless Telemonitoring of Noninvasive Fetal ECG via Block Sparse Bayesian Learning
• Bilinear Generalized Approximate Message Passing
• Compressive Phase Retrieval via Generalized Approximate Message Passing
• Trainable ISTA for Sparse Signal Recovery
• Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models
• A GAMP Based Low Complexity Sparse Bayesian Learning Algorithm
• Type I and Type II Bayesian Methods for Sparse Signal Recovery using Scale Mixtures
• Efficient DOA Estimation Method for Reconfigurable Intelligent Surfaces Aided UAV Swarm
• Two-Dimensional Pattern-Coupled Sparse Bayesian Learning via Generalized Approximate Message Passing
• Channel Estimation for One-Bit Multiuser Massive MIMO Using Conditional GAN
• Recursive Recovery of Sparse Signal Sequences from Compressive Measurements: A Review
• Compressive Sensing with Prior Support Quality Information and Application to Massive MIMO Channel Estimation with Temporal Correlation
• A Unified Bayesian Inference Framework for Generalized Linear Models
• A Factor Graph Approach to Joint OFDM Channel Estimation and Decoding in Impulsive Noise Environments
• Near optimal compressed sensing without priors: Parametric SURE Approximate Message Passing
• Parametric Bilinear Generalized Approximate Message Passing
• Joint Channel, Data, and Radar Parameter Estimation for AFDM Systems in Doubly-Dispersive Channels
• On the Performance of Turbo Signal Recovery with Partial DFT Sensing Matrices
• Approximate Message Passing with Unitary Transformation for Robust Bilinear Recovery
• Location Identification of Power Line Outages Using PMU Measurements with Bad Data
• An Asymptotically MSE-Optimal Estimator based on Gaussian Mixture Models
• An Empirical-Bayes Approach to Recovering Linearly Constrained Non-Negative Sparse Signals
• Reliable OFDM Receiver with Ultra-Low Resolution ADC
• Super-Resolution Blind Channel-and-Signal Estimation for Massive MIMO with One-Dimensional Antenna Array
• Swift-Link: A compressive beam alignment algorithm for practical mmWave radios
• Bilinear Recovery using Adaptive Vector-AMP
• Asymptotically Optimal Estimation Algorithm for the Sparse Signal with Arbitrary Distributions
• Approximate Message Passing Algorithm with Universal Denoising and Gaussian Mixture Learning
• Performance Analysis and Approximate Message Passing Detection of Orthogonal Time Sequency Multiplexing Modulation
• FedVQCS: Federated Learning via Vector Quantized Compressed Sensing
• Parameterless Optimal Approximate Message Passing
• Approximate Message Passing with Restricted Boltzmann Machine Priors
• Performance Analysis of Approximate Message Passing for Distributed Compressed Sensing
• Variance State Propagation for Structured Sparse Bayesian Learning
• Binary Linear Classification and Feature Selection via Generalized Approximate Message Passing
• Joint Channel-Estimation/Decoding with Frequency-Selective Channels and Few-Bit ADCs
• Bayes-Optimal Unsupervised Learning for Channel Estimation in Near-Field Holographic MIMO
• Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA
• Optimal Data Detection in Large MIMO
• Channel Estimation in Broadband Millimeter Wave MIMO Systems with Few-Bit ADCs
• Joint CFO and Channel Estimation in Millimeter Wave Systems with One-Bit ADCs
• Unifying Message Passing Algorithms Under the Framework of Constrained Bethe Free Energy Minimization
• Sparse Multinomial Logistic Regression via Approximate Message Passing
• Joint Sparsity Pattern Learning Based Channel Estimation for Massive MIMO-OTFS Systems
• Concise Derivation of Complex Bayesian Approximate Message Passing via Expectation Propagation
• Blind Data Detection in Massive MIMO via ${\ell }_3$-norm Maximization over the Stiefel Manifold
• Inference in Deep Networks in High Dimensions
• Empirical Bayes and Full Bayes for Signal Estimation
• Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians
• Approximate Message Passing with Nearest Neighbor Sparsity Pattern Learning
• Approximate Message Passing with Parameter Estimation for Heavily Quantized Measurements
• Compressed Sensing via Universal Denoising and Approximate Message Passing
• Expectation-Maximization-Aided Hybrid Generalized Expectation Consistent for Sparse Signal Reconstruction
• Bayesian Optimal Approximate Message Passing to Recover Structured Sparse Signals
• Multi-user passive beamforming in RIS-aided communications and experimental validations
• Fixed Points of Generalized Approximate Message Passing with Arbitrary Matrices
• Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization
• 1-Bit Compressive Sensing via Approximate Message Passing with Built-in Parameter Estimation
• Sample Distortion for Compressed Imaging
• Compressive Computed Tomography Reconstruction through Denoising Approximate Message Passing
• Application of compressed sensing to genome wide association studies and genomic selection
• Sparse Bayesian Learning Approach for Discrete Signal Reconstruction
• User Activity Detection and Channel Estimation for Grant-Free Random Access in LEO Satellite-Enabled Internet-of-Things
• Statistical Physics and Information Theory Perspectives on Linear Inverse Problems
• JCR70: A Low-Complexity Millimeter-Wave Proof-of-Concept Platform for A Fully-Digital MIMO Joint Communication-Radar
• One-bit LFMCW Radar: Spectrum Analysis and Target Detection
• Gridless Angular Domain Channel Estimation for mmWave Massive MIMO System With One-Bit Quantization Via Approximate Message Passing
• MmWave MIMO Communication with Semi-Passive RIS: A Low-Complexity Channel Estimation Scheme
• A Probabilistic Bayesian Approach to Recover $R_2^{\ast }$ map and Phase Images for Quantitative Susceptibility Mapping
• Compressive Sensing Based Joint Activity and Data Detection for Grant-Free Massive IoT Access
• Expectation Propagation based Line Spectral Estimation
• Message passing-based joint CFO and channel estimation in millimeter wave systems with one-bit ADCs
• Computationally Efficient Sparse Bayesian Learning via Generalized Approximate Message Passing
• Sparse Signal Recovery using Generalized Approximate Message Passing with Built-in Parameter Estimation
• Vector Approximate Message Passing Algorithm for Structured Perturbed Sensing Matrix
• Grid-less Variational Bayesian Inference of Line Spectral from Quantized Samples
• High-Dimensional CSI Acquisition in Massive MIMO: Sparsity-Inspired Approaches
• Channel Estimation via Gradient Pursuit for MmWave Massive MIMO Systems with One-Bit ADCs
• Effective Learning of a GMRF Mixture Model
• Empirical Bayes PCA in high dimensions
• RIDNet Assisted cGAN Based Channel Estimation for One-Bit ADC mmWave MIMO Systems
• An adaptive shortest-solution guided decimation approach to sparse high-dimensional linear regression
• Learning based signal detection for MIMO systems with unknown noise statistics
• D-OAMP: A Denoising-based Signal Recovery Algorithm for Compressed Sensing
• An Overview of Multi-Processor Approximate Message Passing
• Wiener Filters in Gaussian Mixture Signal Estimation with Infinity-Norm Error
• Asymptotic normality in linear regression with approximately sparse structure
• Bayesian Convolutional Neural Networks for Compressed Sensing Restoration
• Bernoulli-Gaussian Approximate Message-Passing Algorithm for Compressed Sensing with 1D-Finite-Difference Sparsity
• Semi-Blind Channel-and-Signal Estimation for Uplink Massive MIMO With Channel Sparsity
• An Efficient Bayesian PAPR Reduction Method for OFDM-Based Massive MIMO Systems
• Sparse Vector Recovery: Bernoulli-Gaussian Message Passing
• Asymptotic Statistical Analysis of Sparse Group LASSO via Approximate Message Passing Algorithm
• State Estimation in Smart Distribution System With Low-Precision Measurements
• Generalized Approximate Message Passing for Massive MIMO mmWave Channel Estimation with Laplacian Prior
• Joint Frame Synchronization and Channel Estimation: Sparse Recovery Approach and USRP Implementation
• Denoising-based Turbo Compressed Sensing
• A Two-stage Approach to Estimate CFO and Channel with One-bit ADCs
• Broadband Synchronization and Compressive Channel Estimation for Hybrid mmWave MIMO Systems