On Convergence of Approximate Message Passing
arXiv:1401.6384 · doi:10.1109/ISIT.2014.6875146
Abstract
Approximate message passing is an iterative algorithm for compressed sensing and related applications. A solid theory about the performance and convergence of the algorithm exists for measurement matrices having iid entries of zero mean. However, it was observed by several authors that for more general matrices the algorithm often encounters convergence problems. In this paper we identify the reason of the non-convergence for measurement matrices with iid entries and non-zero mean in the context of Bayes optimal inference. Finally we demonstrate numerically that when the iterative update is changed from parallel to sequential the convergence is restored.
5 pages, 3 figures
References in corpus (1)
Cited by in corpus (15)
- Trainable ISTA for Sparse Signal Recovery
- An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
- A GAMP Based Low Complexity Sparse Bayesian Learning Algorithm
- Adaptive Damping and Mean Removal for the Generalized Approximate Message Passing Algorithm
- Approximate message-passing decoder and capacity-achieving sparse superposition codes
- Phase transitions and sample complexity in Bayes-optimal matrix factorization
- Joint Activity Detection and Channel Estimation in Cell-Free Massive MIMO Networks with Massive Connectivity
- Random Access in C-RAN for User Activity Detection with Limited-Capacity Fronthaul
- Bilinear Recovery using Adaptive Vector-AMP
- Convolutional Approximate Message-Passing
- Intensity-only optical compressive imaging using a multiply scattering material and a double phase retrieval approach
- Blind Sensor Calibration using Approximate Message Passing
- Performance Analysis of Cell-Free Massive MIMO Systems with Massive Connectivity
- Phase transition in binary compressed sensing based on -norm minimization
- Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions