Sparse Estimation with the Swept Approximated Message-Passing Algorithm

Abstract

Approximate Message Passing (AMP) has been shown to be a superior method for inference problems, such as the recovery of signals from sets of noisy, lower-dimensionality measurements, both in terms of reconstruction accuracy and in computational efficiency. However, AMP suffers from serious convergence issues in contexts that do not exactly match its assumptions. We propose a new approach to stabilizing AMP in these contexts by applying AMP updates to individual coefficients rather than in parallel. Our results show that this change to the AMP iteration can provide theoretically expected, but hitherto unobtainable, performance for problems on which the standard AMP iteration diverges. Additionally, we find that the computational costs of this swept coefficient update scheme is not unduly burdensome, allowing it to be applied efficiently to signals of large dimensionality.

11 pages, 3 figures, implementation available at https://github.com/eric-tramel/SwAMP-Demo

References in corpus (2)

• Message Passing Algorithms for Compressed Sensing
• Message-Passing Estimation from Quantized Samples

Cited by in corpus (18)

• Adaptive Damping and Mean Removal for the Generalized Approximate Message Passing Algorithm
• Compressive Hyperspectral Imaging via Approximate Message Passing
• Compressive Imaging via Approximate Message Passing with Image Denoising
• Unitary Approximate Message Passing for Sparse Bayesian Learning
• Approximate Message Passing with Unitary Transformation
• Location Identification of Power Line Outages Using PMU Measurements with Bad Data
• Approximate Message Passing Algorithm with Universal Denoising and Gaussian Mixture Learning
• Fixed Points of Generalized Approximate Message Passing with Arbitrary Matrices
• Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization
• Generalized Approximate Message Passing for Cosparse Analysis Compressive Sensing
• Fast phase retrieval for high dimensions: A block-based approach
• Memory Approximate Message Passing
• S-AMP for Non-linear Observation Models
• Capacity Optimal Generalized Multi-User MIMO: A Theoretical and Practical Framework
• Sparse Bayesian Learning Using Approximate Message Passing with Unitary Transformation
• An Overview of Multi-Processor Approximate Message Passing
• An adaptive shortest-solution guided decimation approach to sparse high-dimensional linear regression
• Approximate Message Passing in Coded Aperture Snapshot Spectral Imaging