Multi-Layer Bilinear Generalized Approximate Message Passing

Abstract

In this paper, we extend the bilinear generalized approximate message passing (BiG-AMP) approach, originally proposed for high-dimensional generalized bilinear regression, to the multi-layer case for the handling of cascaded problem such as matrix-factorization problem arising in relay communication among others. Assuming statistically independent matrix entries with known priors, the new algorithm called ML-BiGAMP could approximate the general sum-product loopy belief propagation (LBP) in the high-dimensional limit enjoying a substantial reduction in computational complexity. We demonstrate that, in large system limit, the asymptotic MSE performance of ML-BiGAMP could be fully characterized via a set of simple one-dimensional equations termed state evolution (SE). We establish that the asymptotic MSE predicted by ML-BiGAMP' SE matches perfectly the exact MMSE predicted by the replica method, which is well known to be Bayes-optimal but infeasible in practice. This consistency indicates that the ML-BiGAMP may still retain the same Bayes-optimal performance as the MMSE estimator in high-dimensional applications, although ML-BiGAMP's computational burden is far lower. As an illustrative example of the general ML-BiGAMP, we provide a detector design that could estimate the channel fading and the data symbols jointly with high precision for the two-hop amplify-and-forward relay communication systems.

arXiv comment61 pages, 16 figures. This paper has been accepted by IEEE Transaction on Signal Processing

References in corpus (20)

• Message Passing Algorithms for Compressed Sensing
• The dynamics of message passing on dense graphs, with applications to compressed sensing
• Massive Connectivity with Massive MIMO-Part I: Device Activity Detection and Channel Estimation
• Bayes-Optimal Joint Channel-and-Data Estimation for Massive MIMO with Low-Precision ADCs
• Bilinear Generalized Approximate Message Passing
• Asymptotic Analysis of MAP Estimation via the Replica Method and Applications to Compressed Sensing
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Efficient High-Dimensional Inference in the Multiple Measurement Vector Problem
• Entropy and mutual information in models of deep neural networks
• Phase transitions and sample complexity in Bayes-optimal matrix factorization
• Belief propagation for joint sparse recovery
• Bayesian Optimal Data Detector for mmWave OFDM System with Low-Resolution ADC
• Generalized Approximate Message Passing for Estimation with Random Linear Mixing
• A basic introduction to large deviations: Theory, applications, simulations
• Multi-Layer Generalized Linear Estimation
• Multi-Layer Bilinear Generalized Approximate Message Passing
• Inference in Multi-Layer Networks with Matrix-Valued Unknowns
• Multiple Measurement Vectors Problem: A Decoupling Property and its Applications
• Estimation for High-Dimensional Multi-Layer Generalized Linear Model -- Part I: The Exact MMSE Estimator
• Estimation for High-Dimensional Multi-Layer Generalized Linear Model -- Part II: The ML-GAMP Estimator

Cited by in corpus (5)

• Multi-Layer Bilinear Generalized Approximate Message Passing
• Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
• Revisiting XL-MIMO Channel Estimation: When Dual-Wideband Effects Meet Near Field
• Deep learning via message passing algorithms based on belief propagation
• Replica Analysis for Generalized Linear Regression with IID Row Prior