Sorry, you need to enable JavaScript to visit this website.

Signal Processing Theory and Methods

SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning

Paper Details

Authors:
Dirk Slock
Submitted On:
6 August 2018 - 9:13am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

dsw18presentation.pdf

(30 downloads)

Subscribe

[1] Dirk Slock, "SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3384. Accessed: Oct. 23, 2018.
@article{3384-18,
url = {http://sigport.org/3384},
author = {Dirk Slock },
publisher = {IEEE SigPort},
title = {SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning},
year = {2018} }
TY - EJOUR
T1 - SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning
AU - Dirk Slock
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3384
ER -
Dirk Slock. (2018). SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning. IEEE SigPort. http://sigport.org/3384
Dirk Slock, 2018. SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning. Available at: http://sigport.org/3384.
Dirk Slock. (2018). "SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning." Web.
1. Dirk Slock. SAVE - Space Alternating Variational Estimation for Sparse Bayesian Learning [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3384

Data-Driven Nonparametric Hypothesis Testing

Paper Details

Authors:
Yixian Liu, Yingbin Liang, Shuguang Cui
Submitted On:
20 April 2018 - 12:55am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

icassp2018_poster_liuyixian.pdf

(202 downloads)

Subscribe

[1] Yixian Liu, Yingbin Liang, Shuguang Cui, "Data-Driven Nonparametric Hypothesis Testing", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3069. Accessed: Oct. 23, 2018.
@article{3069-18,
url = {http://sigport.org/3069},
author = {Yixian Liu; Yingbin Liang; Shuguang Cui },
publisher = {IEEE SigPort},
title = {Data-Driven Nonparametric Hypothesis Testing},
year = {2018} }
TY - EJOUR
T1 - Data-Driven Nonparametric Hypothesis Testing
AU - Yixian Liu; Yingbin Liang; Shuguang Cui
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3069
ER -
Yixian Liu, Yingbin Liang, Shuguang Cui. (2018). Data-Driven Nonparametric Hypothesis Testing. IEEE SigPort. http://sigport.org/3069
Yixian Liu, Yingbin Liang, Shuguang Cui, 2018. Data-Driven Nonparametric Hypothesis Testing. Available at: http://sigport.org/3069.
Yixian Liu, Yingbin Liang, Shuguang Cui. (2018). "Data-Driven Nonparametric Hypothesis Testing." Web.
1. Yixian Liu, Yingbin Liang, Shuguang Cui. Data-Driven Nonparametric Hypothesis Testing [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3069

Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution


Hyperspectral super-resolution (HSR) is a problem of recovering a high-spectral-spatial-resolution image from a multispectral measurement and a hyperspectral measurement, which have low spectral and spatial resolutions, respectively. We consider a low-rank structured matrix factorization formulation for HSR, which is a non-convex large-scale optimization problem. Our contributions contain both computational and theoretical aspects.

Paper Details

Authors:
Ruiyuan Wu, Chun-Hei Chan, Hoi-To Wai, Wing-Kin Ma, and Xiao Fu
Submitted On:
19 April 2018 - 10:39pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP 2018 modified.pdf

(153 downloads)

Subscribe

[1] Ruiyuan Wu, Chun-Hei Chan, Hoi-To Wai, Wing-Kin Ma, and Xiao Fu, "Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3057. Accessed: Oct. 23, 2018.
@article{3057-18,
url = {http://sigport.org/3057},
author = {Ruiyuan Wu; Chun-Hei Chan; Hoi-To Wai; Wing-Kin Ma; and Xiao Fu },
publisher = {IEEE SigPort},
title = {Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution},
year = {2018} }
TY - EJOUR
T1 - Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution
AU - Ruiyuan Wu; Chun-Hei Chan; Hoi-To Wai; Wing-Kin Ma; and Xiao Fu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3057
ER -
Ruiyuan Wu, Chun-Hei Chan, Hoi-To Wai, Wing-Kin Ma, and Xiao Fu. (2018). Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution. IEEE SigPort. http://sigport.org/3057
Ruiyuan Wu, Chun-Hei Chan, Hoi-To Wai, Wing-Kin Ma, and Xiao Fu, 2018. Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution. Available at: http://sigport.org/3057.
Ruiyuan Wu, Chun-Hei Chan, Hoi-To Wai, Wing-Kin Ma, and Xiao Fu. (2018). "Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution." Web.
1. Ruiyuan Wu, Chun-Hei Chan, Hoi-To Wai, Wing-Kin Ma, and Xiao Fu. Hi, BCD! Hybrid Inexact Block Coordinate Descent for Hyperspectral Super-Resolution [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3057

EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM


Convolutional sparse representations allow modeling an entire image as an alternative to the more common independent patch-based
formulations. Although many approaches have been proposed to efficiently solve the convolutional dictionary learning (CDL) problem,
their computational performance is constrained by the dictionary update stage. In this work, we include two improvements to existing

Paper Details

Authors:
Gustavo Silva, Paul Rodriguez
Submitted On:
19 April 2018 - 3:39pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_3908.pdf

(87 downloads)

Subscribe

[1] Gustavo Silva, Paul Rodriguez, "EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3012. Accessed: Oct. 23, 2018.
@article{3012-18,
url = {http://sigport.org/3012},
author = {Gustavo Silva; Paul Rodriguez },
publisher = {IEEE SigPort},
title = {EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM},
year = {2018} }
TY - EJOUR
T1 - EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM
AU - Gustavo Silva; Paul Rodriguez
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3012
ER -
Gustavo Silva, Paul Rodriguez. (2018). EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM. IEEE SigPort. http://sigport.org/3012
Gustavo Silva, Paul Rodriguez, 2018. EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM. Available at: http://sigport.org/3012.
Gustavo Silva, Paul Rodriguez. (2018). "EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM." Web.
1. Gustavo Silva, Paul Rodriguez. EFFICIENT CONVOLUTIONAL DICTIONARY LEARNING USING PARTIAL UPDATE FAST ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3012

Robust PCA via Dictionary Based Outlier Pursuit

Paper Details

Authors:
Xingguo Li, Jineng Ren, Sirisha Rambhatla, Yangyang Xu, Jarvis Haupt
Submitted On:
19 April 2018 - 2:27pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP18_poster.pdf

(121 downloads)

Keywords

Additional Categories

Subscribe

[1] Xingguo Li, Jineng Ren, Sirisha Rambhatla, Yangyang Xu, Jarvis Haupt, "Robust PCA via Dictionary Based Outlier Pursuit", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2997. Accessed: Oct. 23, 2018.
@article{2997-18,
url = {http://sigport.org/2997},
author = { Xingguo Li; Jineng Ren; Sirisha Rambhatla; Yangyang Xu; Jarvis Haupt },
publisher = {IEEE SigPort},
title = {Robust PCA via Dictionary Based Outlier Pursuit},
year = {2018} }
TY - EJOUR
T1 - Robust PCA via Dictionary Based Outlier Pursuit
AU - Xingguo Li; Jineng Ren; Sirisha Rambhatla; Yangyang Xu; Jarvis Haupt
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2997
ER -
Xingguo Li, Jineng Ren, Sirisha Rambhatla, Yangyang Xu, Jarvis Haupt. (2018). Robust PCA via Dictionary Based Outlier Pursuit. IEEE SigPort. http://sigport.org/2997
Xingguo Li, Jineng Ren, Sirisha Rambhatla, Yangyang Xu, Jarvis Haupt, 2018. Robust PCA via Dictionary Based Outlier Pursuit. Available at: http://sigport.org/2997.
Xingguo Li, Jineng Ren, Sirisha Rambhatla, Yangyang Xu, Jarvis Haupt. (2018). "Robust PCA via Dictionary Based Outlier Pursuit." Web.
1. Xingguo Li, Jineng Ren, Sirisha Rambhatla, Yangyang Xu, Jarvis Haupt. Robust PCA via Dictionary Based Outlier Pursuit [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2997

Probability Reweighting in Social Learning: Optimality and Suboptimality


This work explores sequential Bayesian binary hypothesis testing in the social learning setup under expertise diversity. We consider a two-agent (say advisor-learner) sequential binary hypothesis test where the learner infers the hypothesis based on the decision of the advisor, a prior private signal, and individual belief. In addition, the agents have varying expertise, in terms of the noise variance in the private signal.

Paper Details

Authors:
Ravi Kiran Raman
Submitted On:
14 April 2018 - 12:41am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2018_Daewon_Seo_v2.pdf

(85 downloads)

Keywords

Additional Categories

Subscribe

[1] Ravi Kiran Raman, "Probability Reweighting in Social Learning: Optimality and Suboptimality", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2794. Accessed: Oct. 23, 2018.
@article{2794-18,
url = {http://sigport.org/2794},
author = {Ravi Kiran Raman },
publisher = {IEEE SigPort},
title = {Probability Reweighting in Social Learning: Optimality and Suboptimality},
year = {2018} }
TY - EJOUR
T1 - Probability Reweighting in Social Learning: Optimality and Suboptimality
AU - Ravi Kiran Raman
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2794
ER -
Ravi Kiran Raman. (2018). Probability Reweighting in Social Learning: Optimality and Suboptimality. IEEE SigPort. http://sigport.org/2794
Ravi Kiran Raman, 2018. Probability Reweighting in Social Learning: Optimality and Suboptimality. Available at: http://sigport.org/2794.
Ravi Kiran Raman. (2018). "Probability Reweighting in Social Learning: Optimality and Suboptimality." Web.
1. Ravi Kiran Raman. Probability Reweighting in Social Learning: Optimality and Suboptimality [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2794

A Nonconvex Variational Approach For Robust Graphical LASSO

Paper Details

Authors:
Emilie Chouzenoux, Jean-Christophe Pesquet
Submitted On:
17 April 2018 - 3:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

Presentation.pdf

(431 downloads)

Presentation.pdf

(694 downloads)

Subscribe

[1] Emilie Chouzenoux, Jean-Christophe Pesquet, "A Nonconvex Variational Approach For Robust Graphical LASSO", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2755. Accessed: Oct. 23, 2018.
@article{2755-18,
url = {http://sigport.org/2755},
author = {Emilie Chouzenoux; Jean-Christophe Pesquet },
publisher = {IEEE SigPort},
title = {A Nonconvex Variational Approach For Robust Graphical LASSO},
year = {2018} }
TY - EJOUR
T1 - A Nonconvex Variational Approach For Robust Graphical LASSO
AU - Emilie Chouzenoux; Jean-Christophe Pesquet
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2755
ER -
Emilie Chouzenoux, Jean-Christophe Pesquet. (2018). A Nonconvex Variational Approach For Robust Graphical LASSO. IEEE SigPort. http://sigport.org/2755
Emilie Chouzenoux, Jean-Christophe Pesquet, 2018. A Nonconvex Variational Approach For Robust Graphical LASSO. Available at: http://sigport.org/2755.
Emilie Chouzenoux, Jean-Christophe Pesquet. (2018). "A Nonconvex Variational Approach For Robust Graphical LASSO." Web.
1. Emilie Chouzenoux, Jean-Christophe Pesquet. A Nonconvex Variational Approach For Robust Graphical LASSO [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2755

A Novel Method for Human Bias Correction of Continuous-time Annotations


Human annotations are of integral value in human behavior studies and in particular for the generation of ground truth for behavior prediction using various machine learning methods. These often subjective human annotations are especially required for studies involving measuring and predicting hidden mental states (e.g. emotions) that cannot effectively be measured or assessed by other means. Human annotations are noisy and prone to the influence of several factors including personal bias, task ambiguity, environmental distractions, and health state.

Paper Details

Authors:
Karel Mundnich, Shrikanth S. Narayanan
Submitted On:
13 April 2018 - 2:06pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

booth_ICASSP_2018.pdf

(102 downloads)

Subscribe

[1] Karel Mundnich, Shrikanth S. Narayanan, "A Novel Method for Human Bias Correction of Continuous-time Annotations", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2735. Accessed: Oct. 23, 2018.
@article{2735-18,
url = {http://sigport.org/2735},
author = {Karel Mundnich; Shrikanth S. Narayanan },
publisher = {IEEE SigPort},
title = {A Novel Method for Human Bias Correction of Continuous-time Annotations},
year = {2018} }
TY - EJOUR
T1 - A Novel Method for Human Bias Correction of Continuous-time Annotations
AU - Karel Mundnich; Shrikanth S. Narayanan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2735
ER -
Karel Mundnich, Shrikanth S. Narayanan. (2018). A Novel Method for Human Bias Correction of Continuous-time Annotations. IEEE SigPort. http://sigport.org/2735
Karel Mundnich, Shrikanth S. Narayanan, 2018. A Novel Method for Human Bias Correction of Continuous-time Annotations. Available at: http://sigport.org/2735.
Karel Mundnich, Shrikanth S. Narayanan. (2018). "A Novel Method for Human Bias Correction of Continuous-time Annotations." Web.
1. Karel Mundnich, Shrikanth S. Narayanan. A Novel Method for Human Bias Correction of Continuous-time Annotations [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2735

FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO


Accelerating the solution of the Lasso problem becomes crucial when scaling to very high dimensional data.

In this paper, we propose a way to combine two existing acceleration techniques: safe screening tests, which simplify the problem by eliminating useless dictionary atoms; and the use of structured dictionaries which are faster to operate with. A structured approximation of the true dictionary is used at the initial stage of the optimization, and we show how to define screening tests which are still safe despite the approximation error.

Paper Details

Authors:
Rémi GRIBONVAL
Submitted On:
24 April 2018 - 7:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides-2018-ICASSP_2.pdf

(108 downloads)

Keywords

Additional Categories

Subscribe

[1] Rémi GRIBONVAL, "FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2720. Accessed: Oct. 23, 2018.
@article{2720-18,
url = {http://sigport.org/2720},
author = {Rémi GRIBONVAL },
publisher = {IEEE SigPort},
title = {FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO},
year = {2018} }
TY - EJOUR
T1 - FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO
AU - Rémi GRIBONVAL
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2720
ER -
Rémi GRIBONVAL. (2018). FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO. IEEE SigPort. http://sigport.org/2720
Rémi GRIBONVAL, 2018. FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO. Available at: http://sigport.org/2720.
Rémi GRIBONVAL. (2018). "FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO." Web.
1. Rémi GRIBONVAL. FASTER AND STILL SAFE: COMBINING SCREENING TECHNIQUES AND STRUCTURED DICTIONARIES TO ACCELERATE THE LASSO [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2720

Sparse Support Recovery via Covariance Estimation


We consider the problem of recovering the common support of a set of
$k$-sparse signals $\{\mathbf{x}_{i}\}_{i=1}^{L}$ from noisy linear
underdetermined measurements of the form
$\{{\Phi} \mathbf{x}_{i}+\mathbf{w}_{i}\}_{i=1}^{L}$ where
${\Phi}\in\rr^{m\times N}$ $(m<N)$ is the sensing matrix and
$\mathbf{w}_{i}$ is the additive noise. We employ a Bayesian setup where we impose a Gaussian prior with zero mean and a
common diagonal covariance matrix $\mathbf{\Gamma}$ across all

icassp_v3.pdf

PDF icon icassp_v3.pdf (236 downloads)

Paper Details

Authors:
Lekshmi Ramesh, Chandra R. Murthy
Submitted On:
13 April 2018 - 4:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_v3.pdf

(236 downloads)

Subscribe

[1] Lekshmi Ramesh, Chandra R. Murthy, "Sparse Support Recovery via Covariance Estimation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2646. Accessed: Oct. 23, 2018.
@article{2646-18,
url = {http://sigport.org/2646},
author = {Lekshmi Ramesh; Chandra R. Murthy },
publisher = {IEEE SigPort},
title = {Sparse Support Recovery via Covariance Estimation},
year = {2018} }
TY - EJOUR
T1 - Sparse Support Recovery via Covariance Estimation
AU - Lekshmi Ramesh; Chandra R. Murthy
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2646
ER -
Lekshmi Ramesh, Chandra R. Murthy. (2018). Sparse Support Recovery via Covariance Estimation. IEEE SigPort. http://sigport.org/2646
Lekshmi Ramesh, Chandra R. Murthy, 2018. Sparse Support Recovery via Covariance Estimation. Available at: http://sigport.org/2646.
Lekshmi Ramesh, Chandra R. Murthy. (2018). "Sparse Support Recovery via Covariance Estimation." Web.
1. Lekshmi Ramesh, Chandra R. Murthy. Sparse Support Recovery via Covariance Estimation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2646

Pages