Research map / Learning theory and algorithms / Optimal transport
Spherical Sliced-Wasserstein
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 SSW instead of SW as the density-estimation loss | exponential map normalizing flow · Earthquake | negative test log likelihood: 0.94 -> 0.84 | Helped |
| Use SSW instead of SW as the density-estimation loss | exponential map normalizing flow · Flood | negative test log likelihood: 1.36 -> 1.26 | Helped |
| Use SSW instead of SW as the density-estimation loss | exponential map normalizing flow · Fire | negative test log likelihood: 0.54 -> 0.23 | Helped |
| Replace SW with SSW and use a spherical prior | SWAE · MNIST | FID: 15.18 -> 14.91 | Helped |
| Replace SW with SSW and use a spherical prior | SWAE · Fashion | FID: 44.78 -> 43.94 | Helped |
| Replace SW with SSW and use a spherical prior | SWAE · CIFAR10 | FID: 98.5 -> 98.57 | Hurt |
Closest papers by meaning
- Tree-Sliced Wasserstein Distance with Nonlinear Projection (ICML 2025 · similarity 0.92)
- Stereographic Spherical Sliced Wasserstein Distances (ICML 2024 · similarity 0.91)
- Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction (AAAI 2025 · similarity 0.91)
- Spherical Tree-Sliced Wasserstein Distance (ICLR 2025 · similarity 0.90)
- Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates (ICML 2024 · similarity 0.89)
- Sliced Wasserstein Estimation with Control Variates (ICLR 2024 · similarity 0.88)
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.