Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
8898209 | Applied and Computational Harmonic Analysis | 2018 | 37 Pages |
Abstract
In this work we show that iterative thresholding and K means (ITKM) algorithms can recover a generating dictionary with K atoms from noisy S sparse signals up to an error ÎµË as long as the initialisation is within a convergence radius, that is up to a logâ¡K factor inversely proportional to the dynamic range of the signals, and the sample size is proportional to Klogâ¡KεËâ2. The results are valid for arbitrary target errors if the sparsity level is of the order of the square root of the signal dimension d and for target errors down to Kââ if S scales as Sâ¤d/(âlogâ¡K).
Keywords
Related Topics
Physical Sciences and Engineering
Mathematics
Analysis
Authors
Karin Schnass,