Research map / Learning theory and algorithms / Matrix and tensor methods
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization
Mingkui Tan, Shijie Xiao, Junbin Gao, Dong Xu, Anton van den Hengel, Qinfeng Shi
Check 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 progressive rank expansion instead of a fixed rank (ablation) | PRP versus PRG · TOY1 matrix completion | convergence speed | Improved |
| Use progressive rank expansion instead of a fixed rank (ablation) | PRP(R) versus PRG(R) · TOY2 matrix completion with outliers | convergence speed | Improved |
| Add robust error regularization and alternating error updates (ablation) | PRG(R) versus PRG · TOY2 matrix completion with outliers | testing RMSE | Improved |
| Add robust error regularization and alternating error updates (ablation) | PRP(R) versus PRP · Yahoo | RMSE: 22.644 -> 22.537 | Improved |
| Add robust error regularization and alternating error updates (ablation) | PRP(R) versus PRP · Movie-10M | RMSE: 0.817 -> 0.815 | Improved |
| Add robust error regularization and alternating error updates (ablation) | PRP(R) versus PRP · Netflix | RMSE: 0.855 -> 0.857 | Hurt |
| Use PRP instead of RP | Matrix completion · Yahoo | RMSE: 23.451 -> 22.644 | Improved |
Closest papers by meaning
- Fast Hybrid Algorithm for Big Matrix Recovery (AAAI 2016 · similarity 0.88)
- Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach (ICML 2021 · similarity 0.87)
- Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold (JMLR 2022 · similarity 0.87)
- Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point (ICML 2024 · similarity 0.85)
- Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion (ICML 2025 · similarity 0.85)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · 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.
