Learned ISTA with Error-based Thresholding for Adaptive Sparse Coding

• URL: http://arxiv.org/abs/2112.10985v2
• Date: Tue, 19 Dec 2023 05:51:09 GMT
• Title: Learned ISTA with Error-based Thresholding for Adaptive Sparse Coding
• Authors: Ziang Li, Kailun Wu, Yiwen Guo, and Changshui Zhang
• Abstract summary: We propose an error-based thresholding mechanism for learned ISTA (LISTA) We show that the proposed EBT mechanism well disentangles the learnable parameters in the shrinkage functions from the reconstruction errors.
• Score: 58.73333095047114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Drawing on theoretical insights, we advocate an error-based thresholding (EBT) mechanism for learned ISTA (LISTA), which utilizes a function of the layer-wise reconstruction error to suggest a specific threshold for each observation in the shrinkage function of each layer. We show that the proposed EBT mechanism well disentangles the learnable parameters in the shrinkage functions from the reconstruction errors, endowing the obtained models with improved adaptivity to possible data variations. With rigorous analyses, we further show that the proposed EBT also leads to a faster convergence on the basis of LISTA or its variants, in addition to its higher adaptivity. Extensive experimental results confirm our theoretical analyses and verify the effectiveness of our methods.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.