An Integral-Based Approach to Orthogonal AMP

Yiyao Cheng; Lei Liu; Li Ping

doi:10.1109/LSP.2020.3047376

An Integral-Based Approach to Orthogonal AMP

Yiyao Cheng^*
, Lei Liu
, Li Ping

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

5 Citations (Scopus)

Abstract

Approximate message passing (AMP) is an iterative signal recovery algorithm for compressive sensing (CS) applications. In this letter, we present an integral-based orthogonal AMP (IB-OAMP) technique that avoids the requirements of AMP (and also the original form of OAMP) on differentiable and separable denoisers. The orthogonality in IB-OAMP can be established using a Monte Carlo method similar to the training stage in a machine-learning algorithm. These features make IB-OAMP attractive to be used in conjunction with some well-studied denoising algorithms.

Original language	English
Pages (from-to)	194-198
Journal	IEEE Signal Processing Letters
Volume	28
Online published	24 Dec 2020
DOIs	https://doi.org/10.1109/LSP.2020.3047376
Publication status	Published - 2021

Research Keywords

Binary phase shift keying
Gram-Schmidt orthogonality
integral-based OAMP
Monte Carlo methods
Noise reduction
Orthogonal approximate message passing
Sensors
Signal processing algorithms
Software algorithms
state evolution
Training

RGC Funding Information

RGC-funded

Access Output

10.1109/LSP.2020.3047376

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{965bfda8f13b4833b7d53bce28eac33c,

title = "An Integral-Based Approach to Orthogonal AMP",

abstract = "Approximate message passing (AMP) is an iterative signal recovery algorithm for compressive sensing (CS) applications. In this letter, we present an integral-based orthogonal AMP (IB-OAMP) technique that avoids the requirements of AMP (and also the original form of OAMP) on differentiable and separable denoisers. The orthogonality in IB-OAMP can be established using a Monte Carlo method similar to the training stage in a machine-learning algorithm. These features make IB-OAMP attractive to be used in conjunction with some well-studied denoising algorithms.",

keywords = "Binary phase shift keying, Gram-Schmidt orthogonality, integral-based OAMP, Monte Carlo methods, Noise reduction, Orthogonal approximate message passing, Sensors, Signal processing algorithms, Software algorithms, state evolution, Training",

author = "Yiyao Cheng and Lei Liu and Li Ping",

year = "2021",

doi = "10.1109/LSP.2020.3047376",

language = "English",

volume = "28",

pages = "194--198",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "IEEE",

}

TY - JOUR

T1 - An Integral-Based Approach to Orthogonal AMP

AU - Cheng, Yiyao

AU - Liu, Lei

AU - Ping, Li

PY - 2021

Y1 - 2021

N2 - Approximate message passing (AMP) is an iterative signal recovery algorithm for compressive sensing (CS) applications. In this letter, we present an integral-based orthogonal AMP (IB-OAMP) technique that avoids the requirements of AMP (and also the original form of OAMP) on differentiable and separable denoisers. The orthogonality in IB-OAMP can be established using a Monte Carlo method similar to the training stage in a machine-learning algorithm. These features make IB-OAMP attractive to be used in conjunction with some well-studied denoising algorithms.

AB - Approximate message passing (AMP) is an iterative signal recovery algorithm for compressive sensing (CS) applications. In this letter, we present an integral-based orthogonal AMP (IB-OAMP) technique that avoids the requirements of AMP (and also the original form of OAMP) on differentiable and separable denoisers. The orthogonality in IB-OAMP can be established using a Monte Carlo method similar to the training stage in a machine-learning algorithm. These features make IB-OAMP attractive to be used in conjunction with some well-studied denoising algorithms.

KW - Binary phase shift keying

KW - Gram-Schmidt orthogonality

KW - integral-based OAMP

KW - Monte Carlo methods

KW - Noise reduction

KW - Orthogonal approximate message passing

KW - Sensors

KW - Signal processing algorithms

KW - Software algorithms

KW - state evolution

KW - Training

UR - https://www.scopus.com/pages/publications/85098803325

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85098803325&origin=recordpage

U2 - 10.1109/LSP.2020.3047376

DO - 10.1109/LSP.2020.3047376

M3 - RGC 21 - Publication in refereed journal

SN - 1070-9908

VL - 28

SP - 194

EP - 198

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

ER -

An Integral-Based Approach to Orthogonal AMP

Abstract

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Massive MIMO Systems with Low-Resolution Analogue to Digital Conversion

GRF: Decentralized IDMA for Machine Type Communications

Cite this

An Integral-Based Approach to Orthogonal AMP

Abstract

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Massive MIMO Systems with Low-Resolution Analogue to Digital Conversion

GRF: Decentralized IDMA for Machine Type Communications

Cite this