The Sparse Recovery Autoencoder

Shanshan Wu
Shanshan Wu
Daniel Niels Holtmann-Rice
Daniel Niels Holtmann-Rice
Dmitry Storcheus
Dmitry Storcheus

arXiv: Machine Learning, Volume abs/1806.10175, 2018.

Cited by: 6|Bibtex|Views71|Links
EI

Abstract:

Linear encoding of sparse vectors is widely popular, but is most 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 $ell_1$ d...More

Code:

Data:

Your rating :
0

 

Tags
Comments