Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
arXiv: Machine Learning, 2019.
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
PPT (Upload PPT)