Research map / Learning theory and algorithms / Matrix and tensor methods
Fast Hybrid Algorithm for Big Matrix Recovery
Tengfei Zhou, Hui Qian, Zebang Shen, Congfu Xu
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 |
|---|---|---|---|
| hybrid solver HADMCG vs ADMM | ADMM · ML10M | CPU time (s): 77.95 -> 53.10 | Improved |
| HADMCG vs ADMM on accuracy | ADMM · ML10M | test RMSE: 0.8101 -> 0.8039 | Improved |
| HADMCG vs APG | APG · NetFlix | CPU time (s): 2259 -> 708.2 | Improved |
| HADMCG vs APG on accuracy | APG · NetFlix | test RMSE: 0.8402 -> 0.8398 | No clear effect |
| HADMCG vs APG | APG · Yahoo | CPU time (s): 15920 -> 7027 | Improved |
| HADMCG vs APG on Yahoo accuracy | APG · Yahoo | test RMSE: 23.10 -> 22.00 | Improved |
| HADMNT (Newton) vs HADMCG (conjugate gradient) as inner solver (ablation) | HADMNT · NetFlix | test RMSE: 0.8498 -> 0.8398 | Improved |
| HADMNT vs HADMCG (ablation) | HADMNT · Yahoo | CPU time (s): 14740 -> 7027 | Improved |
| HADMCG vs fixed-rank LRGeomCG | LRGeomCG · ML10M | test RMSE: 0.8246 -> 0.8039 | Improved |
| HADMCG vs Active ALT | Active ALT · ML10M | CPU time (s): 1609 -> 53.10 | Improved |
| HADMCG vs MMBS | MMBS · ML10M | CPU time (s): 28760 -> 53.10 | Improved |
| hybrid solvers on noiseless synthetic matrix recovery | ADMM, APG, MMBS, Active ALT · synthetic 5000x5000 noiseless | ROV/RMSE vs time | Improved |
Closest papers by meaning
- Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization (CVPR 2016 · similarity 0.88)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · similarity 0.88)
- Efficient Active Manifold Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization (JMLR 2024 · similarity 0.88)
- Local and Global Linear Convergence of General Low-Rank Matrix Recovery Problems (AAAI 2022 · similarity 0.87)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (ICLR 2024 · similarity 0.86)
- Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation (ICLR 2025 · similarity 0.86)
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.
