Research map / Learning theory and algorithms / Matrix and tensor methods
Riemannian Submanifold Tracking on Low-Rank Algebraic Variety
Qian Li, Zhichao Wang
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 |
|---|---|---|---|
| RIST (eta=0.04) instead of IALM | RPCA solver · 1000x1000 RPCA, rank 5% | RRE: 3.3e-7 -> 2.7e-8 | Improved |
| RIST (eta=0.04) instead of IALM | RPCA solver · 1000x1000 RPCA, rank 5% | time (s): 30.6 -> 29.1 | Improved |
| RIST (eta=0.04) instead of EALM | RPCA solver · 500x500 RPCA, rank 1% | time (s): 11.0 -> 5.0 | Improved |
| RIST (eta=0.04) instead of LSADM | RPCA solver · 500x500 RPCA, rank 5% | time (s): 77.6 -> 9.8 | Improved |
| RIST versus IALM on accuracy at small size | RPCA solver · 500x500 RPCA, rank 1% | RRE: 8.9e-8 -> 6.4e-8 | Improved |
| increase rank-estimation threshold eta from 0.04 to 0.05 (ablation) | RIST · RPCA synthetic (Table 1) | RRE: 2.7e-8 vs 2.8e-8 (1000, 5%) | No clear effect |
| RIST rank tracking instead of fixed-rank given true rank | matrix completion · Synthetic MC, rank 30/100/150 | estimated rank: 29, 103, 148 | Improved |
| RIST instead of qGeom/RP/ScGrass | matrix completion · Movie-10M, Jester-all | NMAE | No clear effect |
Closest papers by meaning
- Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning (ICML 2023 · similarity 0.88)
- Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method (ICML 2025 · similarity 0.86)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · similarity 0.86)
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.86)
- Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion (ICML 2025 · similarity 0.86)
- Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity (ICML 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.
