Research map / Learning theory and algorithms / Optimal transport
Subspace Robust 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 SRW instead of the standard Wasserstein distance | empirical measures with moderate-to-high Gaussian noise · 20-D Gaussians | relative distance error under noise | Helped |
| use SRW with dimension k matched to the signal dimension | empirical measures sampled from a fragmented hypercube · Fragmented Hypercube | ability to identify signal dimension | Helped |
| use SRW with dimension k matched to the signal dimension | empirical measures sampled from a disk and annulus · Disk to Annulus | ability to identify signal dimension | Helped |
| use SRW rather than standard Wasserstein transport plans | empirical measures from a fragmented hypercube · Fragmented Hypercube | robustness of geodesics to statistical noise | Helped |
| use SRW rather than standard Wasserstein transport plans | empirical measures from a disk and annulus · Disk to Annulus | robustness of geodesics to statistical noise | Helped |
Closest papers by meaning
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.87)
- Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation (NeurIPS 2026 · similarity 0.87)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 2024 · similarity 0.87)
- Tree-Sliced Wasserstein Distance with Nonlinear Projection (ICML 2025 · similarity 0.87)
- Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization (ICML 2025 · similarity 0.86)
- Linear Partial Gromov-Wasserstein Embedding (ICLR 2025 · 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.