Research map / Probabilistic and scientific modeling / Variational and generative sampling
Optimal transport mapping via input convex neural networks
Ashok Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason Lee
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 |
|---|---|---|---|
| Represent the transport map as the gradient of a convex neural network and train it with the proposed minimax objective | Optimal transport from Q to P · Checkerboard and mixture of eight Gaussians | transport-map quality | Improved |
| Use a gradient-based transport map rather than a continuous neural-network generator | Generative transport to targets with disconnected supports · Checkerboard and mixture of eight Gaussians | spurious probability mass between supports | Improved |
| Train for the optimal transport map rather than using a WGAN generator as an arbitrary transport | Transport map learning · Checkerboard, different random initializations | sensitivity to initialization | Improved |
| Relax the convexity constraint on g and add a penalty for negative weights | Our approach · Optimal transport training | optimization convergence speed | Improved |
Closest papers by meaning
- Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport (NeurIPS 2024 · similarity 0.90)
- Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan (ICML 2025 · similarity 0.89)
- Generative Conditional Distributions by Neural (Entropic) Optimal Transport (ICML 2024 · similarity 0.89)
- Analyzing and Improving Optimal-Transport-based Adversarial Networks (ICLR 2024 · similarity 0.89)
- Improving Neural Optimal Transport via Displacement Interpolation (ICLR 2025 · similarity 0.89)
- On the Relation between Rectified Flows and Optimal Transport (NeurIPS 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.
