Research map / Learning theory and algorithms / Matrix and tensor methods
Online High Rank Matrix Completion
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 kernelized factorization for high-rank matrix completion instead of low-rank completion | Matrix completion · Synthetic data | relative error | Helped |
| Use online KFMC instead of other online completion methods | Online matrix completion · Synthetic data | recovery error | Helped |
| Use out-of-sample KFMC instead of other out-of-sample methods | Out-of-sample completion · Synthetic data | recovery error | Helped |
| Use KFMC with an RBF kernel instead of the compared HRMC methods | Matrix completion followed by subspace clustering · Hopkins155 (1R2RC and 1R2TCR) | clustering error | Helped |
| Use HRMC instead of LRMC | Matrix completion · CMU motion capture data | recovery error | Helped |
| Use online completion instead of offline completion | Matrix completion · CMU motion capture data | recovery error | Helped |
| Use OL-KFMC with an RBF kernel instead of the other methods | Online matrix completion · CMU motion capture data | recovery error | Helped |
| Use online KFMC instead of VMC, NLMC, or offline KFMC | Matrix completion · CMU motion capture data | time cost (second): VMC 370; NLMC 610; KFMC (Poly) 170; KFMC (RBF) 190; OL-KFMC (Poly) 16; OL-KFMC (RBF) 19 | Helped |
| Use the RBF kernel instead of the polynomial kernel | KFMC · Experiments | recovery error | Helped |
| Increase the momentum parameter | KFMC optimization · Synthetic data | convergence speed | Helped |
Closest papers by meaning
- A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness (NeurIPS 2024 · similarity 0.89)
- RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees (NeurIPS 2025 · similarity 0.89)
- Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion (NeurIPS 2024 · similarity 0.88)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.88)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.88)
- Deep-Union Completion (AAAI 2025 · 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.