Rigorous Dynamics of Expectation-Propagation-Based Signal Recovery from Unitarily Invariant Measurements
arXiv:1701.05653
Abstract
This paper investigates sparse signal recovery based on expectation propagation (EP) from unitarily invariant measurements. A rigorous analysis is presented for the state evolution (SE) of an EP-based message-passing algorithm in the large system limit, where both input and output dimensions tend to infinity at an identical speed. The main result is the justification of an SE formula conjectured by Ma and Ping.
arXiv commentAccepted for presentation at ISIT2017. A short version of arXiv:1701.05284
References in corpus (6)
- Message Passing Algorithms for Compressed Sensing
- Expectation Propagation for approximate Bayesian inference
- Turbo Compressed Sensing with Partial DFT Sensing Matrix
- Multivariate normal approximation using exchangeable pairs
- Analysis of CDMA systems that are characterized by eigenvalue spectrum
- The Mutual Information in Random Linear Estimation
Cited by in corpus (6)
- Model-Driven Deep Learning for MIMO Detection
- Capacity-Achieving MIMO-NOMA: Iterative LMMSE Detection
- Hybrid Approximate Message Passing
- A New Insight into GAMP and AMP
- TARM: A Turbo-type Algorithm for Affine Rank Minimization
- Layered Belief Propagation for Low-complexity Large MIMO Detection Based on Statistical Beams