Research map / Probabilistic and scientific modeling / Variational and generative sampling
Generalized Sliced Wasserstein Distances
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 homogeneous polynomial (degree 3) defining function instead of linear slicing (SW) (ablation) | GSW flows (L=10 projections) · 5 toy target distributions (25-Gaussians, 8-Gaussians, Swiss Roll, Half Moons, Circle) | 2-Wasserstein distance to target | Helped |
| choice of defining function (linear, circular, polynomial deg 3 or 5) (ablation) | GSW flows · toy target distributions | 2-Wasserstein distance to target | Mixed |
| use GSW with polynomial defining function instead of SW in the SWAE objective (ablation) | SWAE on MNIST · MNIST latent/prior matching | 2-Wasserstein distance | Helped |
| replace GSW (10 random projections) by max-GSW (one optimized projection) (ablation) | GSW flows · toy target distributions | 2-Wasserstein distance to target | Helped |
| use Max-GSWAE instead of WAE-GAN for latent matching | Wasserstein auto-encoder on MNIST · latent vs prior distribution | 2-Wasserstein distance | No clear effect |
Closest papers by meaning
- Tree-Sliced Wasserstein Distance with Nonlinear Projection (ICML 2025 · similarity 0.90)
- Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis (ICML 2025 · similarity 0.89)
- Sliced Wasserstein Estimation with Control Variates (ICLR 2024 · similarity 0.89)
- Distance-Based Tree-Sliced Wasserstein Distance (ICLR 2025 · similarity 0.88)
- Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions (NeurIPS 2024 · similarity 0.88)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · 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.