Generalization analysis of an unfolding network for analysis-based Compressed Sensing

Abstract

Unfolding networks have shown promising results in the Compressed Sensing (CS) field. Yet, the investigation of their generalization ability is still in its infancy. In this paper, we perform a generalization analysis of a state-of-the-art ADMM-based unfolding network, which jointly learns a decoder for CS and a sparsifying redundant analysis operator. To this end, we first impose a structural constraint on the learnable sparsifier, which parametrizes the network's hypothesis class. For the latter, we estimate its Rademacher complexity. With this estimate in hand, we deliver generalization error bounds -- which scale like the square root of the number of layers -- for the examined network. Finally, the validity of our theory is assessed and numerical comparisons to a state-of-the-art unfolding network are made, on synthetic and real-world datasets. Our experimental results demonstrate that our proposed framework complies with our theoretical findings and outperforms the baseline, consistently for all datasets.

References in corpus (9)

• The Cosparse Analysis Model and Algorithms
• ${\ell }^1$-Analysis Minimization and Generalized (Co-)Sparsity: When Does Recovery Succeed?
• Dictionary Learning for Blind One Bit Compressed Sensing
• LADMM-Net: An Unrolled Deep Network For Spectral Image Fusion From Compressive Data
• Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variables
• Robust analysis ${\ell }_1$-recovery from Gaussian measurements and total variation minimization
• ADMM-DAD net: a deep unfolding network for analysis compressed sensing
• DECONET: an Unfolding Network for Analysis-based Compressed Sensing with Generalization Error Bounds
• Spark Deficient Gabor Frame Provides a Novel Analysis Operator for Compressed Sensing