Learned Extragradient ISTA with Interpretable Residual Structures 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. Moreover, most LISTA methods use the soft thresholding function, which has been found to cause a large estimation bias. Therefore, we propose a thresholding function for ELISTA instead of soft thresholding. From a theoretical perspective, we prove that our method attains linear convergence. Through ablation experiments, the improvements of our method on the network structure and the thresholding function are verified in practice. Extensive empirical results verify the advantages of our method.

Authors

• Yangyang Li National Engineering Laboratory for Risk Perception and Prevention
• Lin Kong
• Fanhua Shang College of Intelligence and Computing, Tianjin University, Tianjin, China
• Yuanyuan Liu School of Artificial Intelligence, Xidian University, China
• Hongying Liu Medical College, Tianjin University, Tianjin, China Peng Cheng Lab, Shenzhen, China
• Zhouchen Lin National Key Lab of General AI, School of Intelligence Science and Technology, Peking University Peng Cheng Laboratory

Keywords

No keywords are indexed for this paper.