Accuracy guarantees for ℓ1-recovery

IEEE Transactions on Information Theory

Volumn 57, Issue 12, 2011, Pages 7818-7839

  Juditsky, Anatoli ^a   Nemirovski, Arkadi ^b  

^a UNIV GRENOBLE ALPES   (France)

^b GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Linear estimation; nonparametric estimation by convex optimization; oracle inequalities; sparse recovery

Indexed keywords

BASIS PURSUITS; DANTZIG SELECTOR; ESTIMATION PERFORMANCE; LINEAR ESTIMATION; NOISY OBSERVATIONS; NON-EUCLIDEAN; NON-PARAMETRIC ESTIMATIONS; ORACLE INEQUALITIES; PERFORMANCE ESTIMATION; RECOVERY ALGORITHMS; SIGNAL SUPPORT; SPARSE RECOVERY; SPARSE SIGNALS; STATISTICAL PROPERTIES;

ALGORITHMS; CONVEX OPTIMIZATION; OPTIMIZATION; RECOVERY; STATISTICAL METHODS;

ESTIMATION;

EID: 83255193471     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2011.2162569     Document Type: Article

References (21)

1. E. D. Andersen and K. D. Andersen, The MOSEK Optimization Tools Manual. Version 5.0 [Online]. Available: http://www.mosek.com
2. P. Bickel, Y. Ritov, and A. B. Tsybakov, "Simultaneous analysis of Lasso and Dantzig selector" Ann. Statist., vol. 37, pp. 1705-1732, 2009.
3. P. Bühlmann and S. van de Geer, "On the conditions used to prove oracle results for the Lasso" Electron. J. Statist., vol. 3, pp. 1360-1392, 2009.
4. F. Bunea, A. B. Tsybakov, and M. H. Wegkamp, "Sparsity oracle inequalities for the Lasso" Electron. J. Stat., vol. 1, pp. 169-194, 2007.
5. E. Candès, J. Romberg, and T. Tao, "Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information" IEEE Trans. Inf. Theory, vol. 52, no. 2, pp. 489-509, Feb. 2006.
6. E. Candès, J. Romberg, and T. Tao, "Stable signal recovery from incomplete and inaccurate measurements" Comm. Pure Appl. Math., vol. 59, pp. 1207-1223, 2006.
7. E. Candès and T. Tao, "The Dantzig selector: Statistical estimation when p is much larger than n" Ann. Statist., vol. 35, pp. 2313-2351, 2007.
8. E. Candès, "The restricted isometry property and its implications for compressed sensing" Comptes Rendus de l'Acad. des Sci., ser. I, vol. 346, pp. 589-592, 2008.
9. D. Donoho, "Statistical estimation and optimal recovery" Ann. Statist., vol. 22, no. 1, pp. 238-270, 1995.
10. q minimization" Proc. Natl. Acad. Sci. USA, vol. 100, pp. 2197-2202, 2003.
11. M. Elad and A. M. Bruckstein, "A generalized uncertainty principle and sparse representation in pairs of p bases" IEEE Trans. Inf. Theory, vol. 48, no. 9, pp. 2558-2567, Sep. 2002.
12. R. Gribonval and M. Nielsen, "Sparse representations in unions of bases" IEEE Trans. Inf. Theory, vol. 49, no. 12, pp. 3320-3325, Dec. 2003.
13. A. Juditsky and A. Nemirovski, "Nonparametric estimation by convex programming" Ann. Statist., vol. 37, no. 5a, pp. 2278-2300, 2009.
14. q minimization" Math. Programm., vol. 127, no. 1, pp. 57-88, 2011.
15. q -recovery of sparse signals with sign restrictions" Math. Programm., vol. 127, no. 1, pp. 89-122, 2011.
16. V.Koltchinskii, "The Dantzig selector and sparsity oracle inequalities" Bernoulli, vol. 15, pp. 799-828, 2009.
17. K. Lounici, "Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators" Elect. J. Statist., vol. 2, pp. 90-102, 2008.
18. N. Meinshausen and B. Yu, "Lasso-type recovery of sparse representations for high-dimensional data" Ann. Statist., vol. 37, pp. 246-270, 2009.
19. S. van de Geer, in The Deterministic Lasso-Seminar for Statistics, 2007 [Online]. Available: ftp://stat.ethz.ch/Research-Reports/140.pdf
20. C.-H. Zhang and J. Huang, "The sparsity and bias of the Lasso selection in highdimensional linear regression" Ann. Statist., vol. 36, pp. 1567-1594, 2008.
21. q regularization" Ann. Statist., vol. 37, pp. 2109-2144, 2009.