Generalized Residual Ratio Thresholding
From MaRDI portal
Publication:6331363
arXiv1912.08637MaRDI QIDQ6331363
Sheetal Kalyani, Sreejith Kallummil
Publication date: 18 December 2019
Abstract: Simultaneous orthogonal matching pursuit (SOMP) and block OMP (BOMP) are two widely used techniques for sparse support recovery in multiple measurement vector (MMV) and block sparse (BS) models respectively. For optimal performance, both SOMP and BOMP require extit{a priori} knowledge of signal sparsity or noise variance. However, sparsity and noise variance are unavailable in most practical applications. This letter presents a novel technique called generalized residual ratio thresholding (GRRT) for operating SOMP and BOMP without the extit{a priori} knowledge of signal sparsity and noise variance and derive finite sample and finite signal to noise ratio (SNR) guarantees for exact support recovery. Numerical simulations indicate that GRRT performs similar to BOMP and SOMP with extit{a priori} knowledge of signal and noise statistics.
Has companion code repository: https://github.com/sreejithkvenugopal/Residual-Ratio-Thresholding
This page was built for publication: Generalized Residual Ratio Thresholding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6331363)
