Research map / Learning theory and algorithms / Matrix and tensor methods
Efficient Active Manifold Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization
Hao Wang, Ye Wang, Xiangyu Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use EIRNAMI (adaptive perturbation, extrapolation, manifold identification) instead of PIRNN with fixed perturbation | PIRNN · Synthetic matrix completion (r*=5) | average relative error: 5.13 × 10−6 -> 6.42 × 10−7 | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Synthetic matrix completion (r*=10) | average relative error: 3.00 × 10−4 -> 2.67 × 10−5 | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Synthetic matrix completion (r*=15) | average relative error: 1.10 × 10−2 -> 9.15 × 10−4 | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Synthetic matrix completion | number of correct rank detections | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Synthetic matrix completion | convergence speed of relative distance | Improved |
| add extrapolation with alpha=0.7 (vs 0, 0.1, 0.3, 0.5, 0.9) (ablation) | IRNAMI · Synthetic matrix completion | convergence / performance | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Color images, random mask (r*=30) | PSNR: 34.47 -> 34.47 | No clear effect |
| use EIRNAMI instead of PIRNN | PIRNN · Color images, block mask (r*=30) | PSNR: 31.00 -> 34.74 | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Color images, block mask (r*=15) | PSNR: 30.46 -> 31.22 | Improved |
| use EIRNAMI instead of PIRNN | PIRNN · Color images, block mask (r*=25) | PSNR: 31.34 -> 33.83 | Improved |
| use EIRNAMI instead of SCp | SCp · Color images, random mask (r*=30) | PSNR: 33.20 -> 34.47 | Improved |
| use EIRNAMI instead of AIRNN | AIRNN · Color images, random mask (r*=30) | PSNR: 22.68 -> 34.47 | Improved |
Closest papers by meaning
- Fast Hybrid Algorithm for Big Matrix Recovery (AAAI 2016 · similarity 0.88)
- Minimizing the Maximal Rank (CVPR 2016 · similarity 0.86)
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.86)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · similarity 0.85)
- Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds (NeurIPS 2026 · similarity 0.85)
- Optimization without Retraction on the Random Generalized Stiefel Manifold (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.
