Research map / Learning theory and algorithms / Matrix and tensor methods
Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence
Yuetian Luo, Anru R. 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 |
|---|---|---|---|
| Use RGN instead of PGD | projected gradient descent · MRI image recovery (100 images) | runtime (seconds): 79.5 -> 39.2 | Improved |
| Use RGN instead of RTR | Riemannian trust region · MRI image recovery (100 images) | runtime (seconds): 104.9 -> 39.2 | Improved |
| Use RGN instead of PGD | projected gradient descent · MRI image recovery (100 images) | relative RMSE: 0.300 -> 0.155 | Improved |
| Use RGN instead of RTR | Riemannian trust region · MRI image recovery (100 images) | relative RMSE: 0.153 -> 0.155 | No clear effect |
| Use RGN instead of RTR | Riemannian trust region · noiseless tensor regression (p=30, r=3) | convergence speed | Improved |
| Use RGN instead of GD, PGD, Alter Mini | first-order and alternating baselines · noiseless and noisy tensor regression (p=30, r=3) | convergence rate and runtime | Improved |
| Use random initialization instead of spectral initialization | RGN · tensor regression and rank-1 projections | sample size needed / stability | Hurt |
| Use RGN initialized with T-HOSVD | RGN · tensor SVD | iterations to converge | Improved |
Closest papers by meaning
- Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements (JMLR 2022 · similarity 0.89)
- Robust High-Order Tensor Compressive Sensing Based on M-Estimators (AAAI 2026 · similarity 0.88)
- Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion (JMLR 2023 · similarity 0.88)
- Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent (JMLR 2026 · similarity 0.88)
- Nonconvex Low-Rank Tensor Completion from Noisy Data (NeurIPS 2019 · similarity 0.88)
- Robust Low-Rank Tensor Recovery with Rectification and Alignment (TPAMI 2019 · similarity 0.87)
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.
