Research map / Learning theory and algorithms / Optimal transport
A fast and accurate splitting method for optimal transport: analysis and implementation
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 |
|---|---|---|---|
| solve the original OT problem directly with Douglas-Rachford splitting instead of using entropic regularization | DROT versus Sinkhorn · Synthetic OT, m=n=512 | accuracy and robustness | Helped |
| use Sinkhorn with entropic regularization | Sinkhorn · Synthetic OT, m=n=512 | accuracy | Hurt |
| change the underlying data statistics while keeping SK2 | SK2 · Synthetic OT | problems unsolved due to numerical errors: nearly 40% | Hurt |
| use DROT rather than Sinkhorn | DROT versus Sinkhorn · Synthetic OT, dimensions 100–20000 | per-iteration runtime | No clear effect |
| use DROT to solve the unregularized OT problem | DROT · Image color transfer | zeros in transport plan: approximately 99% | Helped |
| use DROT instead of Sinkhorn | DROT versus Sinkhorn · Synthetic OT | iteration complexity: O(1/ε^2) -> O(1/ε) | Helped |
| fuse update, reductions, and stopping-criterion computations in the GPU kernel | DROT GPU implementation · Synthetic OT | memory operations per iteration: 2.5 | Helped |
Closest papers by meaning
- A Truncated Newton Method for Optimal Transport (ICLR 2025 · similarity 0.93)
- Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport (NeurIPS 2024 · similarity 0.91)
- Progressive Entropic Optimal Transport Solvers (NeurIPS 2024 · similarity 0.88)
- Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space (NeurIPS 2026 · similarity 0.88)
- The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport (ICML 2025 · similarity 0.88)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 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.