Research map / Probabilistic and scientific modeling / Variational and generative sampling
Large Scale Optimal Transport and Mapping Estimation
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 |
|---|---|---|---|
| Learn a parametric Monge map instead of using only the discrete barycentric projection | Proposed OT domain adaptation · MNIST→USPS | accuracy (%): 68.84 -> 77.92 | Helped |
| Learn a parametric Monge map instead of using only the discrete barycentric projection | Proposed OT domain adaptation · USPS→MNIST | accuracy (%): 57.55 -> 60.02 | Helped |
| Learn a parametric Monge map instead of using only the discrete barycentric projection | Proposed OT domain adaptation · SVHN→MNIST | accuracy (%): 58.87 -> 61.11 | Helped |
| Use L2 rather than entropy regularization (ablation) | Barycentric-projection OT domain adaptation · MNIST→USPS | accuracy (%): 68.84 -> 67.8 | Hurt |
| Use L2 rather than entropy regularization (ablation) | Barycentric-projection OT domain adaptation · USPS→MNIST | accuracy (%): 57.55 -> 57.47 | No clear effect |
| Use L2 rather than entropy regularization (ablation) | Barycentric-projection OT domain adaptation · SVHN→MNIST | accuracy (%): 58.87 -> 60.56 | Helped |
| Use L2 rather than entropy regularization (ablation) | Monge-map OT domain adaptation · MNIST→USPS | accuracy (%): 77.92 -> 72.61 | Hurt |
| Use L2 rather than entropy regularization (ablation) | Monge-map OT domain adaptation · USPS→MNIST | accuracy (%): 60.02 -> 60.50 | Helped |
| Use L2 rather than entropy regularization (ablation) | Monge-map OT domain adaptation · SVHN→MNIST | accuracy (%): 61.11 -> 62.88 | Helped |
| Use the stochastic dual algorithm rather than a stochastic semi-dual approach | Regularized OT computation · CAVE spectral transfer, 250000 samples | training loss convergence speed | Helped |
Closest papers by meaning
- Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan (ICML 2025 · similarity 0.91)
- Estimation of Stochastic Optimal Transport Maps (NeurIPS 2025 · similarity 0.90)
- Improving Neural Optimal Transport via Displacement Interpolation (ICLR 2025 · similarity 0.89)
- Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport (NeurIPS 2024 · similarity 0.88)
- Analyzing and Improving Optimal-Transport-based Adversarial Networks (ICLR 2024 · similarity 0.88)
- Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation (ICLR 2024 · 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.