Research map / Learning theory and algorithms / Matrix and tensor methods
Non-Convex Matrix Completion and Related Problems via Strong Duality
Maria-Florina Balcan, Yingyu Liang, Zhao Song, David P. Woodruff, Hongyang 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 r* minimization (known rank) instead of nuclear norm minimization | matrix completion · Hopkins 155 (avg over 155 tasks, 5% observed) | relative error: 0.8249 -> 0.8114 | Improved |
| use r* minimization instead of nuclear norm minimization | matrix completion · Hopkins 155 (avg over 155 tasks, 10% observed) | relative error: 0.5689 -> 0.5409 | Improved |
| use r* minimization instead of nuclear norm at 5% observations on individual tasks | matrix completion · Hopkins 155 tasks #1-#5 (5% observed) | relative error: task #1: 0.7438 -> 0.5948; task #4: 0.8500 -> 0.9583 | Mixed |
| use r* minimization instead of nuclear norm at 10% observations | matrix completion · Hopkins 155 tasks #1-#5 (10% observed) | relative error: task #5: 0.4476 -> 0.4477 | No clear effect |
| use r* minimization instead of nuclear norm minimization | matrix completion · Synthetic 100x100 and 200x200 exact recovery | success region of exact recovery | Improved |
Closest papers by meaning
- A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery (ICML 2018 · similarity 0.91)
- Robust Matrix Factorization by Majorization Minimization (TPAMI 2017 · similarity 0.89)
- Scalable Robust Matrix Factorization with Nonconvex Loss (NeurIPS 2018 · similarity 0.89)
- Semidefinite Programming versus Burer-Monteiro Factorization for Matrix Sensing (AAAI 2023 · similarity 0.89)
- No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis (ICML 2017 · similarity 0.89)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · 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.
