Research map / Learning theory and algorithms / Optimal transport
Hilbert Sinkhorn Divergence for Optimal Transport
Check 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 the Hilbert Sinkhorn kernel (PSK) instead of the strongest listed baseline (PHK) | SVM · ANT | classification accuracy: 91.3 ± 0.5 -> 92.7 ± 0.3 | Helped |
| Use PSK instead of the strongest listed baseline (PWG) | SVM · FISH | classification accuracy: 79.3 ± 0.6 -> 78.8 ± 0.6 | Hurt |
| Use PSK instead of the strongest listed baseline (PWG) | SVM · BIRD | classification accuracy: 72.2 ± 1.4 -> 73.2 ± 0.4 | Helped |
| Use PSK instead of the strongest listed baseline (PHK) | SVM · HUMAN | classification accuracy: 73.2 ± 0.4 -> 74.3 ± 0.5 | Helped |
| Use PSK instead of the strongest listed baseline (PWK) | SVM · OCTOPUS | classification accuracy: 84.4 ± 0.5 -> 85.9 ± 0.2 | Helped |
| Use PSK instead of the strongest listed baseline (PWK) | SVM · LIMB | classification accuracy: 72.8 ± 0.8 -> 74.2 ± 0.6 | Helped |
| Use PSK instead of the strongest listed baseline (PWK) | SVM · BEAR | classification accuracy: 73.9 ± 0.4 -> 73.4 ± 0.6 | Hurt |
| Use PSK instead of the strongest listed baseline (PWK) | SVM · SYN | classification accuracy: 97.4 ± 1.9 -> 98.1 ± 0.7 | Helped |
| Use PSK instead of the strongest listed baseline (PWK) | SVM · REAL | classification accuracy: 66.3 ± 2.0 -> 68.9 ± 0.5 | Helped |
| Use PSK instead of PHK | SVM · OUTEX00000 CLBP-S | texture recognition accuracy: 73.8 ± 1.0 -> 75.3 ± 1.0 | Helped |
| Use PSK instead of PHK | SVM · OUTEX00000 CLBP-M | texture recognition accuracy: 60.3 ± 1.4 -> 62.3 ± 1.4 | Helped |
| Use PSK instead of RBF | SVM · USPS | classification error | Helped |
Closest papers by meaning
- Accelerating Sinkhorn algorithm with sparse Newton iterations (ICLR 2024 · similarity 0.88)
- On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods (AAAI 2024 · similarity 0.87)
- Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport (NeurIPS 2024 · similarity 0.86)
- Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence (NeurIPS 2024 · similarity 0.86)
- Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation (NeurIPS 2026 · similarity 0.85)
- Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridge (ICML 2025 · 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.