Learned Interpretable Residual Extragradient ISTA for Sparse Coding
This work addresses a specific bottleneck in sparse coding algorithms for researchers in signal processing or machine learning, offering an incremental improvement with theoretical guarantees.
The authors tackled the limitation of serial connections in learned iterative shrinkage thresholding algorithms (LISTA) for sparse coding by proposing ELISTA, a novel extragradient-based method with a residual structure, which achieves linear convergence and demonstrates empirical advantages.
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.