mlsanityData to 7 Oct 2026

Learned Interpretable Residual Extragradient ISTA for Sparse Coding

arXiv 2106.11970 ↗First posted 22 Jun 2021cs.LG math.OC stat.COcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

26 of 48 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  5. 2018Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholdscited by 83
  6. 2014Deep Unfolding: Model-Based Inspiration of Novel Deep Architecturescited by 76
  7. 2017One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Modelscited by 67
  8. 2017Learned D-AMP: Principled Neural Network based Compressive Image Recoverycited by 65
  9. 2015Gated Feedback Recurrent Neural Networkscited by 54
  10. 2016Convolutional Neural Networks Analyzed via Convolutional Sparse Codingcited by 51
  11. 2016Maximal Sparsity with Deep Networks?cited by 29
  12. 2019Learning step sizes for unfolded sparse codingcited by 29
14 more
  1. 2017Learned Convolutional Sparse Codingcited by 26
  2. 2020RNA Secondary Structure Prediction By Learning Unrolled Algorithmscited by 24
  3. 2020Ada-LISTA: Learned Solvers Adaptive to Varying Modelscited by 22
  4. 2019Rethinking the CSC Model for Natural Imagescited by 21
  5. 2018On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networkscited by 20
  6. 2019Differentiable Linearized ADMMcited by 18
  7. 2019Deep Network Classification by Scattering and Homotopy Dictionary Learningcited by 17
  8. 2017Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learningcited by 14
  9. 2016Tradeoffs between Convergence Speed and Reconstruction Accuracy in Inverse Problemscited by 12
  10. 2016Understanding Trainable Sparse Coding via Matrix Factorizationcited by 12
  11. 2018Multi-Layer Sparse Coding: The Holistic Waycited by 9
  12. 2017From Bayesian Sparsity to Gated Recurrent Netscited by 7
  13. 2016Extragradient Method in Optimization: Convergence and Complexitycited by 2
  14. 2020A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problemscited by 2

Built on by

Not cited yet.