Stable recovery of sparse signals and an oracle inequality

  • Authors:
  • Tony Tony Cai;Lie Wang;Guangwu Xu

  • Affiliations:
  • Department of Statistics, The Wharton School, University of Pennsylvania, Philadelphia, PA;Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA;Department of Electrical Engineering and Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI

  • Venue:
  • IEEE Transactions on Information Theory
  • Year:
  • 2010

Quantified Score

Hi-index 754.90

Visualization

Abstract

This article considers sparse signal recovery in the presence of noise. A mutual incoherence condition which was previously used for exact recovery in the noiseless case is shown to be sufficient for stable recovery in the noisy case. Furthermore, the condition is proved to be sharp. A specific counterexample is given. In addition, an oracle inequality is derived under the mutual incoherence condition in the case of Gaussian noise.