Research map / Learning theory and algorithms / Matrix and tensor methods
Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add partial weight coupling and support selection | LISTA · Set 11 test images, 20% | PSNR (dB): 28.17 -> 28.25 | Helped |
| Add partial weight coupling and support selection | LISTA · Set 11 test images, 30% | PSNR (dB): 30.43 -> 30.54 | Helped |
| Add partial weight coupling and support selection | LISTA · Set 11 test images, 40% | PSNR (dB): 32.75 -> 32.87 | Helped |
| Add partial weight coupling and support selection | LISTA · Set 11 test images, 50% | PSNR (dB): 34.26 -> 34.60 | Helped |
| Add partial weight coupling and support selection | LISTA · Set 11 test images, 60% | PSNR (dB): 35.99 -> 36.39 | Helped |
| Couple the layer weights using W2 = I - W1A | LISTA · Sparse vector recovery, noiseless and noisy simulations | NMSE | No clear effect |
| Add support selection that exempts largest-magnitude entries from thresholding | LISTA-CP · Sparse vector recovery, noiseless and noisy simulations | NMSE | Helped |
| Add support selection that exempts largest-magnitude entries from thresholding | LISTA-CP · Sparse vector recovery, noiseless simulations, layers k >= 10 | NMSE | Helped |
Closest papers by meaning
- Learning step sizes for unfolded sparse coding (NeurIPS 2019 · similarity 0.92)
- Learned Extragradient ISTA with Interpretable Residual Structures for Sparse Coding (AAAI 2021 · similarity 0.88)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.86)
- Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery (AAAI 2024 · similarity 0.85)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.85)
- Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.