Research map / Learning theory and algorithms / Matrix and tensor methods
A Proximal Alternating Direction Method for Semi-Definite Rank Minimization
Ganzhao Yuan, Bernard Ghanem
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 PADM (exact MPEC formulation) instead of LPAM and other convex or non-convex relaxations | PADM · sensor network localization, Gaussian noise | rank and dist | Improved |
| use TAM instead of FM among convex methods | TAM · sensor network localization | rank | Improved |
| use LDHM instead of convex methods TAM and FM | LDHM · sensor network localization | rank and dist | Mixed |
| use penalty decomposition (PDA) instead of other methods | PDA · sensor network localization | dist | Hurt |
| increase the noise level s | all methods · sensor network localization | dist | Hurt |
| increase the sampling ratio r | all methods · sensor network localization | dist | Improved |
| stop PADM after about 5 iterations instead of running to full convergence | PADM · d=3 sensor localization | rank and dist | No clear effect |
Closest papers by meaning
- A Unified Alternating Direction Method of Multipliers by Majorization Minimization (TPAMI 2017 · similarity 0.88)
- Linearized Alternating Direction Method with Penalization for Nonconvex and Nonsmooth Optimization (AAAI 2016 · similarity 0.86)
- Affine Rank Minimization via Asymptotic Log-Det Iteratively Reweighted Least Squares (JMLR 2025 · similarity 0.86)
- No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis (ICML 2017 · similarity 0.85)
- Recovery guarantee of weighted low-rank approximation via alternating minimization (ICML 2016 · similarity 0.85)
- Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation (ICLR 2025 · similarity 0.84)
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.
