Research map / Learning theory and algorithms / Matrix and tensor methods
Minimizing the Maximal Rank
Check 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 |
|---|---|---|---|
| Use the proposed maximal-rank method instead of Manifold Denoising | USPS Digits denoising · USPS Digits | PSNR: 15.6656 -> 17.5231 | Helped |
| Use the proposed maximal-rank method instead of BM3D | Single-image denoising · Lena | PSNR: 29.1560 -> 28.6064 | Hurt |
| Use the proposed maximal-rank method instead of BM3D | Single-image denoising · Cameraman | PSNR: 24.7322 -> 26.0663 | Helped |
| Use the proposed maximal-rank method instead of the local rank function | Linear shape basis estimation · Hand | Reconstruction error: 0.474 -> 0.474 | No clear effect |
| Use the proposed maximal-rank method instead of the local rank function | Linear shape basis estimation · Banner | Reconstruction error: 6.54 · 10⁷ -> 4.73 · 10⁷ | Helped |
| Use the proposed maximal-rank method instead of the local rank function | Linear shape basis estimation · Book | Reconstruction error: 0.121 -> 0.121 | No clear effect |
Closest papers by meaning
- On the Power of Truncated SVD for General High-rank Matrix Estimation Problems (NeurIPS 2017 · similarity 0.87)
- Learning-Based Low-Rank Approximations (NeurIPS 2019 · similarity 0.87)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (ICLR 2024 · similarity 0.86)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.86)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · similarity 0.86)
- Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation (ICLR 2025 · 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.