Research map / Learning theory and algorithms / Optimal transport
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm
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 |
|---|---|---|---|
| Analyze Sinkhorn for entropic regularized UOT with KL marginal penalties | Sinkhorn · Discrete UOT, measures with at most n components | complexity: \widetilde{\mathcal{O}}(n^2/ \varepsilon) versus \bigOtil(n^2/\varepsilon^2) | Helped |
Closest papers by meaning
- Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport (NeurIPS 2024 · similarity 0.89)
- On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods (AAAI 2024 · similarity 0.88)
- A Truncated Newton Method for Optimal Transport (ICLR 2025 · similarity 0.88)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 2024 · similarity 0.88)
- Accelerating Sinkhorn algorithm with sparse Newton iterations (ICLR 2024 · similarity 0.87)
- Light Unbalanced Optimal Transport (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.