Research map / Learning theory and algorithms / Optimal transport
The Monge Gap: A Regularizer to Learn All Transport Maps
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 |
|---|---|---|---|
| Add the Monge gap and conservative regularizer | MLP · Korotin benchmark, dimensions d ≥ 16 | L2 unexplained variance | Helped |
| Add the Monge gap and conservative regularizer | MLP · 4i single-cell data | Sinkhorn divergence | Helped |
| Add the Monge gap and conservative regularizer | MLP · scRNA single-cell data | Sinkhorn divergence | Helped |
| Use a vanilla MLP instead of the ICNN neural dual formulation | Single-cell response prediction · 4i and scRNA single-cell data | Sinkhorn divergence | Helped |
| Increase the Monge-gap and conservativity regularization weights (ablation) | MLP · Korotin benchmark, d = 32 | L2 unexplained variance | Helped |
| Use different reference measures ρ that contain the source support (ablation) | Monge-gap-regularized MLP · Synthetic measures, ℓ2 distance cost | Sinkhorn divergence | No clear effect |
Closest papers by meaning
- Estimation of Stochastic Optimal Transport Maps (NeurIPS 2025 · similarity 0.89)
- Progressive Entropic Optimal Transport Solvers (NeurIPS 2024 · similarity 0.88)
- Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation (NeurIPS 2026 · similarity 0.88)
- Expected Sliced Transport Plans (ICLR 2025 · similarity 0.87)
- Hierarchical Refinement: Optimal Transport to Infinity and Beyond (ICML 2025 · similarity 0.87)
- Learning Elastic Costs to Shape Monge Displacements (NeurIPS 2024 · similarity 0.87)
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.