CFP last date
22 April 2024
Reseach Article

Stability Analysis of LASSO and Dantzig Selector via Constrained Minimal Singular Value of Gaussian Sensing Matrices

Published on May 2015 by Oliver James
An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds
Foundation of Computer Science USA
ICCTAC2015 - Number 2
May 2015
Authors: Oliver James
80455375-64df-4db5-97d0-25a71e64682f

Oliver James . Stability Analysis of LASSO and Dantzig Selector via Constrained Minimal Singular Value of Gaussian Sensing Matrices. An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds. ICCTAC2015, 2 (May 2015), 1-5.

@article{
author = { Oliver James },
title = { Stability Analysis of LASSO and Dantzig Selector via Constrained Minimal Singular Value of Gaussian Sensing Matrices },
journal = { An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds },
issue_date = { May 2015 },
volume = { ICCTAC2015 },
number = { 2 },
month = { May },
year = { 2015 },
issn = 0975-8887,
pages = { 1-5 },
numpages = 5,
url = { /proceedings/icctac2015/number2/20924-2020/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds
%A Oliver James
%T Stability Analysis of LASSO and Dantzig Selector via Constrained Minimal Singular Value of Gaussian Sensing Matrices
%J An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds
%@ 0975-8887
%V ICCTAC2015
%N 2
%P 1-5
%D 2015
%I International Journal of Computer Applications
Abstract

In this paper, we introduce a new framework for interpreting the existing theoretical stability results of sparse signal recovery algorithms in practical terms. Our framework is built on the theory of constrained minimal singular values of Gaussian sensing matrices. Adopting our framework, we study the stability of two algorithms, namely LASSO and Dantzig selector. We demonstrate that for a given stability parameter (noise sensitivity), there exits a minimum undersampling ratio above which the recovery algorithms are guaranteed to be stable.

References
  1. Barry C. Arnold, N. Balakrishnan, and H. N. Nagaraja. A First Course in Order Statistics. SIAM, Philadelphia.
  2. Emmanuel J. Candes. The restricted isometry property and its implications for compressed sensing. C. R. Acad. Sci. Paris, Ser. I.
  3. Emmanuel J. Candes and Terence Tao. Decoding by linear programming. IEEE Transactions on Information Theory.
  4. Enrique Castillo, Ali S. Hadi, N. Balakrishnan, and Jose M. Sarabia. Extreme Value and Related Models with Applications in Engineering and Science. John Wiley and Sons, New York.
  5. L. Canto E Castro. Uniform rates of convergence in extremevalue theory: Normal and gamma models. Annales de la Facult des sciences de l'Universit de Clermont, Srie Probabilits et applications.
  6. Paul Embrechts, Claudia Kluppelberg, and Thomas Mikosch. Modeling Extremal Events for Insurance and Finance. Springer Verlag, New York.
  7. I. S. Gradshteyn and I. M. Ryzhik. Table of Integrals, Series, and Products. Academics Press, San Diego.
  8. A. K. Gupta and D. K. Nagar. Matrix Variate Distributions. Chapman and Hall, Florida.
  9. Hwan-Chol Jang, Chang-Hyeong Yoon, Eui-Heon Chung, Won-Shik Choi, and Heung-No Lee. Speckle suppression via sparse representation for wide-field imaging through turbid media. Optics Express.
  10. Gongguo Tang and Arye Nehorai. Performance analysis of sparse recovery based on constrained minimal singular values. IEEE Transactions on Signal Processing.
  11. Brendt Wohlberg. Noise sensitivity of sparse signal representations: Reconstruction error bounds for the inverse problem. IEEE Transactions on Signal Processing.
  12. Hui Zhang and Lizhi Cheng. On the constrained minimal singular values for sparse signal recovery. IEEE Signal Processing Letters.
Index Terms

Computer Science
Information Sciences

Keywords

Compressed Sensing Constrained Minimal Singular Value Stability Analysis Convex Algorithms Undersampling Analysis