Research map / Learning theory and algorithms / Matrix and tensor methods
Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
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 FGSR instead of nuclear-norm regularization | Low-rank matrix completion · Noisy synthetic matrix completion | recovery error | Helped |
| Use FGSR instead of max norm or F-nuclear norm | Low-rank matrix completion · Noiseless synthetic matrix completion, high missing rate | recovery error | Helped |
| Use FGSR instead of max norm or F-nuclear norm | Low-rank matrix completion · Noisy synthetic matrix completion | robustness to initial rank | Helped |
| Use FGSR instead of nuclear norm or F-nuclear norm | Robust PCA · Synthetic RPCA, high noise density | recovery error | Helped |
| Use FGSR instead of max norm or F-nuclear norm | Low-rank matrix completion · MovieLens-1M | NMAE and RMSE | Helped |
| Use FGSR1/2 instead of FGSR2/3 | Low-rank matrix completion · MovieLens-1M | NMAE and RMSE | Helped |
| Decrease Schatten-p from 1 to 2/9 (ablation) | FGSR-based noisy matrix completion · Noisy synthetic matrix completion | recovery error | Helped |
| Decrease Schatten-p further below 2/9 (ablation) | FGSR-based noisy matrix completion · Noisy synthetic matrix completion | recovery error | No clear effect |
| Increase the initial rank (ablation) | FGSR2/3 and FGSR1/2 · Noisy synthetic matrix completion | recovery error | No clear effect |
| Increase the initial rank (ablation) | FGSR2/3 and FGSR1/2 · MovieLens-1M | NMAE and RMSE | No clear effect |
| Increase the initial rank (ablation) | FGSR2/3 and FGSR1/2 · Synthetic RPCA | recovery error | No clear effect |
| Use FGSR1/2 instead of FGSR2/3 | Robust PCA · Synthetic RPCA, high noise density | recovery error | Helped |
Closest papers by meaning
- Nearly Optimal Robust Matrix Completion (ICML 2017 · similarity 0.89)
- RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees (NeurIPS 2025 · similarity 0.89)
- Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization (NeurIPS 2021 · similarity 0.89)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.88)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (ICLR 2024 · similarity 0.88)
- Fast exact recovery of noisy matrix from few entries: the infinity norm approach (NeurIPS 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.