Research map / Optimization / Nonconvex and smooth optimization
Bilinear Parameterization for Non-Separable Singular Value Penalties
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the bilinear formulation instead of ADMM with weighted nuclear norm regularization | Structure-from-motion matrix recovery · Cathedral, Door, and École | log-loss: Cathedral: -2.4548 -> -3.8110; Door: -1.6247 -> -4.6275; École: -1.6869 -> -4.4264 | Helped |
| Use the bilinear formulation instead of ADMM with the best reported LI or SV weights | Structure-from-motion matrix recovery · Back, Heart, and Paper | log-loss: Back: -5.2560 -> -5.2863; Heart: -5.0829 -> -5.1153; Paper: -5.8509 -> -5.9023 | Helped |
| Replace ADMM with the bilinear method | Non-rigid structure from motion · Articulated, Balloon, Paper, Stretch, and Tearing | log-loss: Articulated: -2.221 -> -2.415; Balloon: -2.529 -> -2.657; Paper: -2.338 -> -2.560; Stretch: -2.395 -> -2.622; Tearing: - | Helped |
| Replace ADMM with the bilinear method | Non-rigid structure from motion · Balloon, Paper, Stretch, and Tearing | reconstruction error (mm): Balloon: 9.29 -> 8.29; Paper: 6.95 -> 6.70; Stretch: 7.83 -> 7.66; Tearing: 29.90 -> 11.26 | Helped |
| Replace ADMM with the bilinear method | Non-rigid structure from motion · Articulated | reconstruction error (mm): 14.55 -> 16.10 | Hurt |
Closest papers by meaning
- A Unified Optimization Framework for Low-Rank Inducing Penalties (CVPR 2020 · similarity 0.88)
- Revisiting the Variable Projection Method for Separable Nonlinear Least Squares Problems (CVPR 2017 · similarity 0.86)
- Cogradient Descent for Bilinear Optimization (CVPR 2020 · similarity 0.85)
- Minimizing the Maximal Rank (CVPR 2016 · similarity 0.84)
- Inexact Newton-type Methods for Optimisation with Nonnegativity Constraints (ICML 2024 · similarity 0.84)
- Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems (AAAI 2024 · similarity 0.83)
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.