Convergence radius and sample complexity of ITKM algorithms for dictionary learning
Volume: 45, Issue: 1, Pages: 22 - 58
Published: Jul 1, 2018
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 ε˜ as long as the initialisation is within a convergence radius, that is up to a logK factor inversely proportional to the dynamic range of the signals, and the sample size is proportional to KlogKε˜−2. The results are valid for arbitrary target errors if the sparsity level...
Paper Details
Title
Convergence radius and sample complexity of ITKM algorithms for dictionary learning
Published Date
Jul 1, 2018
Volume
45
Issue
1
Pages
22 - 58
Citation AnalysisPro
You’ll need to upgrade your plan to Pro
Looking to understand the true influence of a researcher’s work across journals & affiliations?
- Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
- Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.
Notes
History