Learned Interpretable Residual Extragradient ISTA for Sparse Coding
arXiv:2106.11970
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.
arXiv commentAccepted for presentation at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
References in corpus (27)
- Discussion of "Least angle regression" by Efron et al
- Rejoinder to "Least angle regression" by Efron et al
- Least Angle Regression
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
- Gated Feedback Recurrent Neural Networks
- Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
- Trainable ISTA for Sparse Signal Recovery
- Learned D-AMP: Principled Neural Network based Compressive Image Recovery
- Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
- Learned Convolutional Sparse Coding
- Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
- Maximal Sparsity with Deep Networks?
- One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
- RNA Secondary Structure Prediction By Learning Unrolled Algorithms
- Differentiable Linearized ADMM
- Rethinking the CSC Model for Natural Images
- From Bayesian Sparsity to Gated Recurrent Nets
- Understanding Trainable Sparse Coding via Matrix Factorization
- A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems