Research map / Learning theory and algorithms / Matrix and tensor methods
Matrix Completion with Noisy Entries and Outliers
Raymond K. W. Wong, Thomas C. M. Lee
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 |
|---|---|---|---|
| replace squared loss with Huber loss (Robust-Impute vs Soft-Impute) | Soft-Impute · Lena inpainting, independent missing, rank 100 | testing error: 0.0581 -> 0.0557 | Improved |
| replace squared loss with Huber loss | Soft-Impute · Lena inpainting, clustered missing, rank 100 | testing error: 0.0760 -> 0.0723 | Improved |
| replace squared loss with Huber loss | Soft-Impute · Lena inpainting, independent missing, rank 125 | training error: 0.0113 -> 0.0252 | Hurt |
| replace squared loss with Huber loss | Soft-Impute · Landsat TM (tuned by MAD) | test MAD: 31.15 -> 28.76 | Improved |
| replace squared loss with Huber loss | Soft-Impute · Landsat TM (tuned by MSE) | test MSE: 45.20 -> 44.63 | Improved |
| replace squared loss with Huber loss when no outliers present | Soft-Impute · Simulation r=10, p=0, q=0.5 | test error | Hurt |
| replace squared loss with Huber loss when 10% outliers present | Soft-Impute · Simulation r=10, p=0.1, q=0.5 | test error | Improved |
| replace squared loss with Huber loss | Soft-Impute · Simulation r=10, q=0.5 | number of SVDs | Hurt |
Closest papers by meaning
- Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling (NeurIPS 2016 · similarity 0.88)
- RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees (NeurIPS 2025 · similarity 0.88)
- Fast exact recovery of noisy matrix from few entries: the infinity norm approach (NeurIPS 2025 · similarity 0.87)
- A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness (NeurIPS 2024 · similarity 0.87)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.86)
- Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting (NeurIPS 2024 · 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.
