Research map / Learning theory and algorithms / Optimal transport
Augmented 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 ASWD instead of DSWD with 10 projections | GAN training · CIFAR10 | FID: 74.2 $\pm$ 3.1 -> 65.7$\pm$3.2 | Helped |
| Use ASWD instead of DSWD with 100 projections | GAN training · CIFAR10 | FID: 66.5 $\pm$ 3.9 -> 62.5$\pm$1.9 | Helped |
| Use ASWD instead of DSWD with 1000 projections | GAN training · CIFAR10 | FID: 62.3 $\pm$ 5.7 -> 59.3$\pm$3.2 | Helped |
| Use ASWD instead of DSWD with 10 projections | GAN training · CelebA | FID: 86.0 $\pm$ 1.4 -> 81.2$\pm$1.3 | Helped |
| Use ASWD instead of DSWD with 100 projections | GAN training · CelebA | FID: 76.1 $\pm$ 3.5 -> 73.2$\pm$2.6 | Helped |
| Use ASWD instead of DSWD with 1000 projections | GAN training · CelebA | FID: 71.3$\pm$4.7 -> 67.4$\pm$2.1 | Helped |
| Use ASWD rather than the compared slice-based distances | Sliced Wasserstein flows · Eight synthetic target distributions | 2-Wasserstein distance | Mixed |
Closest papers by meaning
- Markovian Sliced Wasserstein Distances: Beyond Independent Projections (NeurIPS 2023 · similarity 0.92)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.91)
- Tree-Sliced Wasserstein Distance with Nonlinear Projection (ICML 2025 · similarity 0.91)
- Sliced Wasserstein Estimation with Control Variates (ICLR 2024 · similarity 0.89)
- Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis (ICML 2025 · similarity 0.89)
- Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction (AAAI 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.