Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling

arXiv: Machine Learning, 2019.

Cited by: 13|Bibtex|Views59|Links
EI

Abstract:

Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a-priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $ell_1$ decoder. The convex $ell_1$ decode...More

Code:

Data:

Your rating :
0

 

Tags
Comments