Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks

no code implementations • 8 Dec 2021 • Ekkehard Schnoor, Arash Behboodi, Holger Rauhut

Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements.

Dictionary Learning Generalization Bounds

Compressive Sensing and Neural Networks from a Statistical Learning Perspective

no code implementations • 29 Oct 2020 • Arash Behboodi, Holger Rauhut, Ekkehard Schnoor

The neural networks in this class are obtained by unfolding iterations of ISTA and learning some of the weights.

Compressive Sensing Dictionary Learning +1