Computer Science – Information Theory
Scientific paper
2008-04-11
IEEE Trans. on Information Theory, vol. 55, no. 12, pp. 5758-5772, December 2009
Computer Science
Information Theory
Submitted to IEEE Transactions on Information Theory
Scientific paper
10.1109/TIT.2009.2032726
The problem of detecting the sparsity pattern of a k-sparse vector in R^n from m random noisy measurements is of interest in many areas such as system identification, denoising, pattern recognition, and compressed sensing. This paper addresses the scaling of the number of measurements m, with signal dimension n and sparsity-level nonzeros k, for asymptotically-reliable detection. We show a necessary condition for perfect recovery at any given SNR for all algorithms, regardless of complexity, is m = Omega(k log(n-k)) measurements. Conversely, it is shown that this scaling of Omega(k log(n-k)) measurements is sufficient for a remarkably simple ``maximum correlation'' estimator. Hence this scaling is optimal and does not require more sophisticated techniques such as lasso or matching pursuit. The constants for both the necessary and sufficient conditions are precisely defined in terms of the minimum-to-average ratio of the nonzero components and the SNR. The necessary condition improves upon previous results for maximum likelihood estimation. For lasso, it also provides a necessary condition at any SNR and for low SNR improves upon previous work. The sufficient condition provides the first asymptotically-reliable detection guarantee at finite SNR.
Fletcher Alyson K.
Goyal Vivek K.
Rangan Sundeep
No associations
LandOfFree
Necessary and Sufficient Conditions on Sparsity Pattern Recovery does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Necessary and Sufficient Conditions on Sparsity Pattern Recovery, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Necessary and Sufficient Conditions on Sparsity Pattern Recovery will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-705808