Improved AMP (IAMP) for non-ideal measurement matrices. Lu, Y. & Dai, W. In 2015 23rd European Signal Processing Conference (EUSIPCO), pages 1746-1750, Aug, 2015.
Paper doi abstract bibtex This paper studies the sparse recovery problem. Of particular interest is the well known approximate message passing (AMP) algorithm. AMP enjoys low computational complexity and good performance guarantees. However, the algorithm and performance analysis heavily rely on the assumption that the measurement matrix is a standard Gaussian random matrix. The main contribution of this paper is an improved AMP (IAMP) algorithm that works better for non-ideal measurement matrices. The algorithm is equivalent to AMP for standard Gaussian random matrices but provides better recovery when the correlations between columns of the measurement matrix deviate from those of the standard Gaussian random matrices. The derivation is based on a modification of the message passing mechanism that removes the conditional independence assumption. Examples are provided to demonstrate the performance improvement of IAMP where both a particularly designed matrix and a matrix from real applications are used.
@InProceedings{7362683,
author = {Y. Lu and W. Dai},
booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},
title = {Improved AMP (IAMP) for non-ideal measurement matrices},
year = {2015},
pages = {1746-1750},
abstract = {This paper studies the sparse recovery problem. Of particular interest is the well known approximate message passing (AMP) algorithm. AMP enjoys low computational complexity and good performance guarantees. However, the algorithm and performance analysis heavily rely on the assumption that the measurement matrix is a standard Gaussian random matrix. The main contribution of this paper is an improved AMP (IAMP) algorithm that works better for non-ideal measurement matrices. The algorithm is equivalent to AMP for standard Gaussian random matrices but provides better recovery when the correlations between columns of the measurement matrix deviate from those of the standard Gaussian random matrices. The derivation is based on a modification of the message passing mechanism that removes the conditional independence assumption. Examples are provided to demonstrate the performance improvement of IAMP where both a particularly designed matrix and a matrix from real applications are used.},
keywords = {compressed sensing;message passing;improved AMP;IAMP;nonideal measurement matrices;sparse recovery problem;approximate message passing algorithm;computational complexity;standard Gaussian random matrix;standard Gaussian random matrices;measurement matrix;standard Gaussian random matrices;Sparse matrices;Standards;Message passing;Approximation algorithms;Signal processing algorithms;Complexity theory;Approximation methods;AMP;compressed sensing;message passing;sparse signal processing;standard Gaussian random matrix},
doi = {10.1109/EUSIPCO.2015.7362683},
issn = {2076-1465},
month = {Aug},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570104631.pdf},
}
Downloads: 0
{"_id":"bSMBp55583zGmW4cS","bibbaseid":"lu-dai-improvedampiampfornonidealmeasurementmatrices-2015","authorIDs":[],"author_short":["Lu, Y.","Dai, W."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Y."],"propositions":[],"lastnames":["Lu"],"suffixes":[]},{"firstnames":["W."],"propositions":[],"lastnames":["Dai"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"Improved AMP (IAMP) for non-ideal measurement matrices","year":"2015","pages":"1746-1750","abstract":"This paper studies the sparse recovery problem. Of particular interest is the well known approximate message passing (AMP) algorithm. AMP enjoys low computational complexity and good performance guarantees. However, the algorithm and performance analysis heavily rely on the assumption that the measurement matrix is a standard Gaussian random matrix. The main contribution of this paper is an improved AMP (IAMP) algorithm that works better for non-ideal measurement matrices. The algorithm is equivalent to AMP for standard Gaussian random matrices but provides better recovery when the correlations between columns of the measurement matrix deviate from those of the standard Gaussian random matrices. The derivation is based on a modification of the message passing mechanism that removes the conditional independence assumption. Examples are provided to demonstrate the performance improvement of IAMP where both a particularly designed matrix and a matrix from real applications are used.","keywords":"compressed sensing;message passing;improved AMP;IAMP;nonideal measurement matrices;sparse recovery problem;approximate message passing algorithm;computational complexity;standard Gaussian random matrix;standard Gaussian random matrices;measurement matrix;standard Gaussian random matrices;Sparse matrices;Standards;Message passing;Approximation algorithms;Signal processing algorithms;Complexity theory;Approximation methods;AMP;compressed sensing;message passing;sparse signal processing;standard Gaussian random matrix","doi":"10.1109/EUSIPCO.2015.7362683","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570104631.pdf","bibtex":"@InProceedings{7362683,\n author = {Y. Lu and W. Dai},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {Improved AMP (IAMP) for non-ideal measurement matrices},\n year = {2015},\n pages = {1746-1750},\n abstract = {This paper studies the sparse recovery problem. Of particular interest is the well known approximate message passing (AMP) algorithm. AMP enjoys low computational complexity and good performance guarantees. However, the algorithm and performance analysis heavily rely on the assumption that the measurement matrix is a standard Gaussian random matrix. The main contribution of this paper is an improved AMP (IAMP) algorithm that works better for non-ideal measurement matrices. The algorithm is equivalent to AMP for standard Gaussian random matrices but provides better recovery when the correlations between columns of the measurement matrix deviate from those of the standard Gaussian random matrices. The derivation is based on a modification of the message passing mechanism that removes the conditional independence assumption. Examples are provided to demonstrate the performance improvement of IAMP where both a particularly designed matrix and a matrix from real applications are used.},\n keywords = {compressed sensing;message passing;improved AMP;IAMP;nonideal measurement matrices;sparse recovery problem;approximate message passing algorithm;computational complexity;standard Gaussian random matrix;standard Gaussian random matrices;measurement matrix;standard Gaussian random matrices;Sparse matrices;Standards;Message passing;Approximation algorithms;Signal processing algorithms;Complexity theory;Approximation methods;AMP;compressed sensing;message passing;sparse signal processing;standard Gaussian random matrix},\n doi = {10.1109/EUSIPCO.2015.7362683},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570104631.pdf},\n}\n\n","author_short":["Lu, Y.","Dai, W."],"key":"7362683","id":"7362683","bibbaseid":"lu-dai-improvedampiampfornonidealmeasurementmatrices-2015","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570104631.pdf"},"keyword":["compressed sensing;message passing;improved AMP;IAMP;nonideal measurement matrices;sparse recovery problem;approximate message passing algorithm;computational complexity;standard Gaussian random matrix;standard Gaussian random matrices;measurement matrix;standard Gaussian random matrices;Sparse matrices;Standards;Message passing;Approximation algorithms;Signal processing algorithms;Complexity theory;Approximation methods;AMP;compressed sensing;message passing;sparse signal processing;standard Gaussian random matrix"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","creationDate":"2021-02-13T17:31:52.493Z","downloads":0,"keywords":["compressed sensing;message passing;improved amp;iamp;nonideal measurement matrices;sparse recovery problem;approximate message passing algorithm;computational complexity;standard gaussian random matrix;standard gaussian random matrices;measurement matrix;standard gaussian random matrices;sparse matrices;standards;message passing;approximation algorithms;signal processing algorithms;complexity theory;approximation methods;amp;compressed sensing;message passing;sparse signal processing;standard gaussian random matrix"],"search_terms":["improved","amp","iamp","non","ideal","measurement","matrices","lu","dai"],"title":"Improved AMP (IAMP) for non-ideal measurement matrices","year":2015,"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}