# Capacity-achieving Sparse Regression Codes via approximate message passing decoding

@article{Rush2015CapacityachievingSR,
title={Capacity-achieving Sparse Regression Codes via approximate message passing decoding},
author={Cynthia Rush and Adam Greig and Ramji Venkataramanan},
journal={2015 IEEE International Symposium on Information Theory (ISIT)},
year={2015},
pages={2016-2020}
}
Sparse superposition codes were recently introduced by Barron and Joseph for reliable communication over the AWGN channel at rates approaching the channel capacity. In this code, the codewords are sparse linear combinations of columns of a design matrix. In this paper, we propose an approximate message passing decoder for sparse superposition codes. The complexity of the decoder scales linearly with the size of the design matrix. The performance of the decoder is rigorously analyzed and it is… CONTINUE READING

#### Citations

##### Publications citing this paper.
Showing 1-10 of 13 extracted citations

## Implementation of Sparse Superposition Codes

IEEE Transactions on Signal Processing • 2017
View 10 Excerpts
Highly Influenced

ArXiv • 2018

## Finite Sample Analysis of Approximate Message Passing Algorithms

IEEE Transactions on Information Theory • 2018

## Near-optimal matrix recovery from random linear measurements

Proceedings of the National Academy of Sciences of the United States of America • 2018

## Analysis of approximate message passing with a class of non-separable denoisers

2017 IEEE International Symposium on Information Theory (ISIT) • 2017
View 1 Excerpt

2017
View 1 Excerpt

## Compressed FEC Codes With Spatial-Coupling

IEEE Communications Letters • 2017

## Orthogonal AMP

IEEE Access • 2017
View 1 Excerpt

## EXIT Chart Analysis of Turbo Compressed Sensing Using Message Passing Dequantization

IEEE Transactions on Signal Processing • 2016
View 1 Excerpt

## Finite-sample analysis of Approximate Message Passing

2016 IEEE International Symposium on Information Theory (ISIT) • 2016

#### References

##### Publications referenced by this paper.
Showing 1-10 of 15 references

## Fast Sparse Superposition Codes Have Near Exponential Error Probability for $R<{\cal C}$

IEEE Transactions on Information Theory • 2014
View 5 Excerpts
Highly Influenced

## The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing

IEEE Transactions on Information Theory • 2010
View 4 Excerpts
Highly Influenced

## High-dimensional regression with random design, including sparse superposition codes

S. Cho
PhD thesis, Yale University, • 2014
View 2 Excerpts

## Replica analysis and approximate message passing decoder for superposition codes

2014 IEEE International Symposium on Information Theory • 2014
View 3 Excerpts

## High-rate sparse superposition codes with iteratively optimal estimates

2012 IEEE International Symposium on Information Theory Proceedings • 2012
View 3 Excerpts

ArXiv • 2012

ArXiv • 2012
View 1 Excerpt

## Generalized approximate message passing for estimation with random linear mixing

2011 IEEE International Symposium on Information Theory Proceedings • 2011
View 2 Excerpts

ArXiv • 2010