Research map / Learning theory and algorithms / Matrix and tensor methods
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning
Xuelong Li, Hongyuan Zhang, Rui Zhang
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 |
|---|---|---|---|
| add column correlation preserving term (ablation) | NCARL · MovieLens-100K | MSE: 0.3905 -> 0.2922 | Improved |
| add column correlation preserving term (ablation) | NCARL · MovieLens-1M | MSE: 0.6481 -> 0.2721 | Improved |
| add column correlation preserving term (ablation) | NCARL · Image-1 (missing rate 0.5) | MSE: 0.1484 -> 0.1476 | Improved |
| add column correlation preserving term (ablation) | NCARL · Image-2 (missing rate 0.5) | MSE: 0.2030 -> 0.2027 | Improved |
| add adaptive correlation learning (ablation) | NCARL · MovieLens-100K | MSE: 0.2922 -> 0.2787 | Improved |
| add adaptive correlation learning (ablation) | NCARL · MovieLens-1M | MSE: 0.2721 -> 0.2542 | Improved |
| add adaptive correlation learning (ablation) | NCARL · Image-1 (missing rate 0.5) | MSE: 0.1476 -> 0.1309 | Improved |
| add adaptive correlation learning (ablation) | NCARL · Image-2 (missing rate 0.5) | MSE: 0.2027 -> 0.1804 | Improved |
| add correlation and adaptive mechanisms (ablation) | NCARL · MovieLens-1M | time (s): 236.4501 -> 260.1178 | Hurt |
| use NCARL surrogate instead of S3LR subspace model | NCARL · Synthetic 1500x1000, missing rate 0.8 | time (s): 1612.7 -> 26.262 | Improved |
| use NCARL instead of nuclear norm | NCARL · Synthetic 4000x3000, missing rate 0.8 | time (s): 2042.9 -> 229.50 | Improved |
| use NCARL instead of S3LR | NCARL · Image-2 (missing rate 0.7) | MSE: 0.1973 -> 0.1991 | Hurt |
Closest papers by meaning
- Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates (NeurIPS 2026 · similarity 0.91)
- A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples (ICML 2021 · similarity 0.90)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.89)
- Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent (NeurIPS 2016 · similarity 0.89)
- 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.
