Research map / Learning theory and algorithms / Matrix and tensor methods
Matrix Completion with Model-free Weighting
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 |
|---|---|---|---|
| Use model-free weighting instead of FLT | Matrix completion · Setting 1, SNR = 1 | RMSE: 1.927(0.004) -> 1.901(0.004) | Helped |
| Use model-free weighting instead of FLT | Matrix completion · Setting 1, SNR = 1 | TE: 1.946(0.004) -> 1.918(0.004) | Helped |
| Use model-free weighting instead of FLT | Matrix completion · Setting 2, SNR = 1 | RMSE: 1.711(0.004) -> 1.716(0.004) | Hurt |
| Use model-free weighting instead of FLT | Matrix completion · Setting 2, SNR = 1 | TE: 1.674(0.004) -> 1.669(0.004) | Helped |
| Use model-free weighting instead of NW | Matrix completion · Setting 3, SNR = 1 | RMSE: 2.668(0.006) -> 2.412(0.006) | Helped |
| Use model-free weighting instead of NW | Matrix completion · Setting 3, SNR = 1 | TE: 2.779(0.007) -> 2.586(0.007) | Helped |
| Use model-free weighting instead of NW | Matrix completion · Setting 1, SNR = 10 | RMSE: 0.405(0.001) -> 0.425(0.001) | Hurt |
| Use model-free weighting instead of NW | Matrix completion · Setting 1, SNR = 10 | TE: 0.422(0.001) -> 0.443(0.001) | Hurt |
| Use model-free weighting instead of FLT | Matrix completion · Setting 2, SNR = 10 | RMSE: 0.409(0.001) -> 0.401(0.001) | Helped |
| Use model-free weighting instead of FLT | Matrix completion · Setting 2, SNR = 10 | TE: 0.426(0.001) -> 0.418(0.001) | Helped |
| Use model-free weighting instead of FLT | Matrix completion · Setting 3, SNR = 10 | RMSE: 0.670(0.002) -> 0.627(0.001) | Helped |
| Use model-free weighting instead of FLT | Matrix completion · Setting 3, SNR = 10 | TE: 0.736(0.002) -> 0.688(0.002) | Helped |
Closest papers by meaning
- A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness (NeurIPS 2024 · similarity 0.90)
- Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting (NeurIPS 2024 · similarity 0.89)
- Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection (ICML 2025 · similarity 0.88)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.88)
- RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees (NeurIPS 2025 · similarity 0.88)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 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.