Research map / Learning theory and algorithms / Optimal transport
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
Read the paperCheck 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 RBCD instead of RGAS | PRW computation · Fragmented Hypercube, n=100, d=20 | CPU time: 0.37 -> 0.14 | Helped |
| Use RABCD instead of RAGAS | PRW computation · Fragmented Hypercube, n=100, d=20 | CPU time: 0.27 -> 0.10 | Helped |
| Use RBCD instead of RGAS | PRW computation · Fragmented Hypercube, d=50, n=1000 | CPU time: 10.25 -> 8.51 | Helped |
| Use RABCD instead of RAGAS | PRW computation · Fragmented Hypercube, d=50, n=1000 | CPU time: 5.39 -> 3.85 | Helped |
| Use RBCD instead of RGAS | PRW computation · Fragmented Hypercube, n=d=500 | CPU time: 13.12 -> 12.75 | Helped |
| Use RABCD instead of RAGAS | PRW computation · Fragmented Hypercube, n=d=500 | CPU time: 8.22 -> 7.97 | Helped |
| Use RBCD instead of RGAS | PRW computation · Fragmented Hypercube, n=10d, d=250 | CPU time: 427.24 -> 354.91 | Helped |
| Use RABCD instead of RAGAS | PRW computation · Fragmented Hypercube, n=10d, d=250 | CPU time: 157.07 -> 129.90 | Helped |
| Use RBCD instead of RGAS | PRW computation · Gaussian distributions, n=100, d=500 | CPU time: 3.63 -> 3.46 | Helped |
| Use RABCD instead of RAGAS | PRW computation · Gaussian distributions, n=100, d=500 | CPU time: 4.73 -> 4.67 | Helped |
| Use RBCD instead of RGAS | PRW computation · Gaussian distributions, d=20, n=500 | CPU time: 7.31 -> 6.41 | Helped |
| Use RABCD instead of RAGAS | PRW computation · Gaussian distributions, d=20, n=500 | CPU time: 2.69 -> 2.31 | Helped |
Closest papers by meaning
- A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance (NeurIPS 2023 · similarity 0.89)
- On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity (ICML 2024 · similarity 0.87)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.87)
- Tree-Sliced Wasserstein Distance with Nonlinear Projection (ICML 2025 · similarity 0.86)
- Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space (NeurIPS 2025 · similarity 0.86)
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.86)
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.