Research map / Learning theory and algorithms / Matrix and tensor methods
A New Theory for Matrix Completion
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 |
|---|---|---|---|
| Replace convex nuclear norm program (2) with bilinear program (9) (nuclear norm on A plus Frobenius on X, p=m) | Matrix completion on synthetic 100x100 matrices · Nonuniform sampling (diagonal-concentrated observations) | number of successfully restored matrices (PSNR>=40dB): +102% | Helped |
| Replace convex nuclear norm program (2) with bilinear program (9) | Matrix completion on synthetic 100x100 matrices · Uniform random sampling | number of successfully restored matrices (PSNR>=40dB): +44% | Helped |
| Use Frobenius-norm bilinear program (8) with p=m and identity initialization instead of nuclear-norm-based version (ablation) | Bilinear program (8) · Synthetic 100x100 matrices | recovery performance relative to convex program (2) | No clear effect |
Closest papers by meaning
- Matrix Completion with Model-free Weighting (ICML 2021 · similarity 0.92)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.91)
- A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness (NeurIPS 2024 · similarity 0.90)
- Fast exact recovery of noisy matrix from few entries: the infinity norm approach (NeurIPS 2025 · similarity 0.89)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.88)
- Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting (NeurIPS 2024 · similarity 0.88)
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.