Research map / Learning theory and algorithms / Optimal transport
On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples
Cheongjae Jang, Jonghyun Won, Soyeon Jun, Chun Kee Chung, Keehyoung Joo, Yung-Kyun Noh
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 sample transport cost features instead of Hausdorff | three-layer FC regressor · Synthetic Poisson example (log r1) | R2 (%): 43.7 -> 81.5 | Improved |
| use sample transport cost features instead of JS divergence bins | three-layer FC regressor · Synthetic Poisson example (|dt|) | R2 (%): 70.3 -> 98.9 | Improved |
| add transport-distance features SD1 to ISI input | FCN · Retina-All | test AUC: 0.945 -> 0.951 | Improved |
| add transport-distance features SD1 to ISI input | InceptionTime · Retina23 | test AUC: 0.889 -> 0.912 | Improved |
| add SD2 to ISI input | FCN · Retina-All | test AUC: 0.945 -> 0.945 | No clear effect |
| add SD1 to ISI input | ResNet · Retina14 | test AUC: 0.967 -> 0.965 | No clear effect |
| use Wasserstein distance instead of KL for amino acid embeddings | minimum distortion embedding · Kendall tau radial order, all residues | Kendall's tau: 0.731 -> 0.807 | Improved |
Closest papers by meaning
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (ICML 2024 · similarity 0.86)
- Wasserstein Distances, Neuronal Entanglement, and Sparsity (ICLR 2025 · similarity 0.86)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.86)
- Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry (ICLR 2025 · similarity 0.86)
- Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformer (ICML 2024 · similarity 0.85)
- Sliced Wasserstein Estimation with Control Variates (ICLR 2024 · similarity 0.85)
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.
