Research map / Probabilistic and scientific modeling / Variational and generative sampling
MAP Inference via Block-Coordinate Frank-Wolfe Algorithm
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 FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · Protein folding | average lower bound: -12970.61 -> -12917.44 | Helped |
| use FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · Synthetic tomography, 2 projections | average lower bound: 265.89 -> 266.12 | Helped |
| use FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · Synthetic tomography, 4 projections | average lower bound: 336.33 -> 337.88 | Helped |
| use FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · Synthetic tomography, 6 projections | average lower bound: 417.76 -> 424.36 | Helped |
| use FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · Sheep Logan 64×64 | average lower bound: 847.87 -> 897.18 | Helped |
| use FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · Sheep Logan 256×256 | average lower bound: 4359.24 -> 4580.06 | Helped |
| use FWMAP instead of ConicBundle | Lagrangean-decomposition MAP inference · 6d scene flow | average lower bound: -2865.61 -> -2864.2 | Helped |
| use compact plane storage instead of explicit plane vectors (ablation) | FWMAP · Protein-folding MRF | speedup per MP-BCFW pass: 25% | Helped |
| choose proximal weight c near 100 rather than larger or smaller tested values (ablation) | FWMAP · Protein-folding MRF instance 1CKK | lower bound over runtime | Helped |
Closest papers by meaning
- Continuous Relaxation of MAP Inference: A Nonconvex Perspective (CVPR 2018 · similarity 0.88)
- Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions (CVPR 2023 · similarity 0.88)
- Asynchronous Parallel Coordinate Minimization for MAP Inference (NeurIPS 2017 · similarity 0.87)
- One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes (ICML 2022 · similarity 0.86)
- MAP Estimation with Denoisers: Convergence Rates and Guarantees (NeurIPS 2025 · similarity 0.85)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 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.