A generalized framework for learning and recovery of structured sparse signals

Justin Ziniel, Sundeep Rangan, Philip Schniter

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We report on a framework for recovering single- or multi-timestep sparse signals that can learn and exploit a variety of probabilistic forms of structure. Message passing-based inference and empirical Bayesian parameter learning form the backbone of the recovery procedure. We further describe an object-oriented software paradigm for implementing our framework, which consists of assembling modular software components that collectively define a desired statistical signal model. Lastly, numerical results for synthetic and real-world structured sparse signal recovery are provided.

Original languageEnglish (US)
Title of host publication2012 IEEE Statistical Signal Processing Workshop, SSP 2012
Pages325-328
Number of pages4
DOIs
StatePublished - 2012
Event2012 IEEE Statistical Signal Processing Workshop, SSP 2012 - Ann Arbor, MI, United States
Duration: Aug 5 2012Aug 8 2012

Other

Other2012 IEEE Statistical Signal Processing Workshop, SSP 2012
CountryUnited States
CityAnn Arbor, MI
Period8/5/128/8/12

Fingerprint

Recovery
Message passing

Keywords

  • compressed sensing
  • dynamic compressed sensing
  • multiple measurement vectors
  • structured sparse signal recovery
  • structured sparsity

ASJC Scopus subject areas

  • Signal Processing

Cite this

Ziniel, J., Rangan, S., & Schniter, P. (2012). A generalized framework for learning and recovery of structured sparse signals. In 2012 IEEE Statistical Signal Processing Workshop, SSP 2012 (pp. 325-328). [6319694] https://doi.org/10.1109/SSP.2012.6319694

A generalized framework for learning and recovery of structured sparse signals. / Ziniel, Justin; Rangan, Sundeep; Schniter, Philip.

2012 IEEE Statistical Signal Processing Workshop, SSP 2012. 2012. p. 325-328 6319694.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ziniel, J, Rangan, S & Schniter, P 2012, A generalized framework for learning and recovery of structured sparse signals. in 2012 IEEE Statistical Signal Processing Workshop, SSP 2012., 6319694, pp. 325-328, 2012 IEEE Statistical Signal Processing Workshop, SSP 2012, Ann Arbor, MI, United States, 8/5/12. https://doi.org/10.1109/SSP.2012.6319694
Ziniel J, Rangan S, Schniter P. A generalized framework for learning and recovery of structured sparse signals. In 2012 IEEE Statistical Signal Processing Workshop, SSP 2012. 2012. p. 325-328. 6319694 https://doi.org/10.1109/SSP.2012.6319694
Ziniel, Justin ; Rangan, Sundeep ; Schniter, Philip. / A generalized framework for learning and recovery of structured sparse signals. 2012 IEEE Statistical Signal Processing Workshop, SSP 2012. 2012. pp. 325-328
@inproceedings{14b157fd1d364db2ac13654ef3106565,
title = "A generalized framework for learning and recovery of structured sparse signals",
abstract = "We report on a framework for recovering single- or multi-timestep sparse signals that can learn and exploit a variety of probabilistic forms of structure. Message passing-based inference and empirical Bayesian parameter learning form the backbone of the recovery procedure. We further describe an object-oriented software paradigm for implementing our framework, which consists of assembling modular software components that collectively define a desired statistical signal model. Lastly, numerical results for synthetic and real-world structured sparse signal recovery are provided.",
keywords = "compressed sensing, dynamic compressed sensing, multiple measurement vectors, structured sparse signal recovery, structured sparsity",
author = "Justin Ziniel and Sundeep Rangan and Philip Schniter",
year = "2012",
doi = "10.1109/SSP.2012.6319694",
language = "English (US)",
isbn = "9781467301831",
pages = "325--328",
booktitle = "2012 IEEE Statistical Signal Processing Workshop, SSP 2012",

}

TY - GEN

T1 - A generalized framework for learning and recovery of structured sparse signals

AU - Ziniel, Justin

AU - Rangan, Sundeep

AU - Schniter, Philip

PY - 2012

Y1 - 2012

N2 - We report on a framework for recovering single- or multi-timestep sparse signals that can learn and exploit a variety of probabilistic forms of structure. Message passing-based inference and empirical Bayesian parameter learning form the backbone of the recovery procedure. We further describe an object-oriented software paradigm for implementing our framework, which consists of assembling modular software components that collectively define a desired statistical signal model. Lastly, numerical results for synthetic and real-world structured sparse signal recovery are provided.

AB - We report on a framework for recovering single- or multi-timestep sparse signals that can learn and exploit a variety of probabilistic forms of structure. Message passing-based inference and empirical Bayesian parameter learning form the backbone of the recovery procedure. We further describe an object-oriented software paradigm for implementing our framework, which consists of assembling modular software components that collectively define a desired statistical signal model. Lastly, numerical results for synthetic and real-world structured sparse signal recovery are provided.

KW - compressed sensing

KW - dynamic compressed sensing

KW - multiple measurement vectors

KW - structured sparse signal recovery

KW - structured sparsity

UR - http://www.scopus.com/inward/record.url?scp=84868222706&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868222706&partnerID=8YFLogxK

U2 - 10.1109/SSP.2012.6319694

DO - 10.1109/SSP.2012.6319694

M3 - Conference contribution

AN - SCOPUS:84868222706

SN - 9781467301831

SP - 325

EP - 328

BT - 2012 IEEE Statistical Signal Processing Workshop, SSP 2012

ER -