Research map / Learning theory and algorithms / Optimal transport
A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
Nathaniel Lahn, Sharath Raghvendra, Kaiyi Zhang
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| replace Sinkhorn (POT, GPU) with the parallel combinatorial algorithm | Optimal transport solver · Synthetic assignment, n=10,000 | GPU running time | Improved |
| replace Sinkhorn with the parallel combinatorial algorithm | Optimal transport solver · Synthetic OT with random supplies/demands, n=10,000 | GPU running time | Improved |
| replace Sinkhorn with the parallel combinatorial algorithm | Optimal transport solver · MNIST assignment, n=10,000 images | GPU running time | Improved |
| replace Sinkhorn with the parallel combinatorial algorithm | Optimal transport solver · Text OT: Count of Monte Cristo, 20News, IMDB (GloVe) | GPU running time | Improved |
| replace Sinkhorn with the parallel combinatorial algorithm | Optimal transport solver · Synthetic, MNIST and text OT | number of parallel rounds | Improved |
| compare against a CUDA-based GPU implementation in addition to PyTorch | Parallel combinatorial algorithm · GPU implementation comparison | running time | Improved |
| match the regularization of Sinkhorn to the cost of the algorithm versus reversed (fix Sinkhorn, search epsilon) | Experimental protocol · All four settings | running time and rounds | No clear effect |
Closest papers by meaning
- Optimal Transport: Fast Probabilistic Approximation with Exact Solvers (JMLR 2019 · similarity 0.89)
- On the Complexity of Approximating Multimarginal Optimal Transport (JMLR 2022 · similarity 0.88)
- A Truncated Newton Method for Optimal Transport (ICLR 2025 · similarity 0.87)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 2024 · similarity 0.86)
- Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space (NeurIPS 2026 · similarity 0.86)
- Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently (NeurIPS 2024 · similarity 0.85)
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.
