Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Lin Kong

Learned Interpretable Residual Extragradient ISTA for Sparse Coding

Jun 22, 2021
Lin Kong, Wei Sun, Fanhua Shang, Yuanyuan Liu, Hongying Liu

Figure 1 for Learned Interpretable Residual Extragradient ISTA for Sparse Coding

Figure 2 for Learned Interpretable Residual Extragradient ISTA for Sparse Coding

Figure 3 for Learned Interpretable Residual Extragradient ISTA for Sparse Coding

Figure 4 for Learned Interpretable Residual Extragradient ISTA for Sparse Coding

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.

* Accepted for presentation at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Via

Access Paper or Ask Questions