Learned Interpretable Residual Extragradient ISTA for Sparse Coding
Abstract
Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. In particular, our algorithm can also provide the interpretability for Res-Net to a certain extent. From a theoretical perspective, we prove that our method attains linear convergence. In practice, extensive empirical results verify the advantages of our method.
Cite
@article{arxiv.2106.11970,
title = {Learned Interpretable Residual Extragradient ISTA for Sparse Coding},
author = {Lin Kong and Wei Sun and Fanhua Shang and Yuanyuan Liu and Hongying Liu},
journal= {arXiv preprint arXiv:2106.11970},
year = {2021}
}
Comments
Accepted for presentation at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI