One for all and all for one: Efficient computation of partial Wasserstein distances on the line

L. Chapel, R. Tavenard
2/12/2026

No official code found. Best implementation: rtavenar/partial_ot_1d (2 stars, last commit 2025-02-04).

Semantic Scholar

Code Implementations(1)

rtavenar/partial_ot_1dCommunity55%

Code for the ICLR2025 paper: "One for all and all for one: Efficient computation of partial Wasserstein distances on the line"

20Python, Jupyter NotebookJul 21, 20231 years ago

Similar Papers

Non-parametric Sensor Noise Modeling and Synthesis

63% match2026

Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency

63% match2 repos342026

Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

63% match2026

Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images

62% match2026

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

62% match2026

The Ramanujan Library - Automated Discovery on the Hypergraph of Integer Relations

62% match1 repo42026

Cite this paper

@article{chapel2026one,
  title  = {One for all and all for one: Efficient computation of partial Wasserstein distances on the line},
  author = {L. Chapel and R. Tavenard},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:562bfe6ca91eec4cc631a4356faaa24eaeecc64e},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/562bfe6ca91eec4cc631a4356faaa24eaeecc64e.svg)](https://codeofpaper.com/paper/562bfe6ca91eec4cc631a4356faaa24eaeecc64e)

Discussion