Sparse Coding with Gated Learned ISTA

Kailun Wu; Yiwen Guo; Ziang Li; Changshui Zhang

ICLR 2020spotlight51 citations

Sparse Coding with Gated Learned ISTA

Kailun Wu, Yiwen Guo, Ziang Li, Changshui Zhang

Abstract

In this paper, we study the learned iterative shrinkage thresholding algorithm (LISTA) for solving sparse coding problems. Following assumptions made by prior works, we first discover that the code components in its estimations may be lower than expected, i.e., require gains, and to address this problem, a gated mechanism amenable to theoretical analysis is then introduced. Specific design of the gates is inspired by convergence analyses of the mechanism and hence its effectiveness can be formally guaranteed. In addition to the gain gates, we further introduce overshoot gates for compensating insufficient step size in LISTA. Extensive empirical results confirm our theoretical findings and verify the effectiveness of our method.

Sparse codingdeep learninglearned ISTAconvergence analysis

BibTeX

@inproceedings{
Wu2020Sparse,
title={Sparse Coding with Gated Learned ISTA},
author={Kailun Wu and Yiwen Guo and Ziang Li and Changshui Zhang},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=BygPO2VKPH}
}