On Scalability of Optimal Transport for Large-Scale Applications

关于大规模应用的最佳传输的可扩展性

• 批准号: 20K19873
• 负责人: LE Thanh Tam
• 金额: $ 2.66万
• 依托单位: The Institute of Statistical Mathematics (2022)Institute of Physical and Chemical Research (2020-2021)
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Early-Career Scientists
• 财政年份: 2020
• 资助国家: 日本
• 起止时间: 2020-04-01 至 2023-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20K19873/
• 关键词: Partial transport; Sobolev transport; Gromov-Wasserstein; Optimal Transport; (unbalanced) measures; Tree metric; Graph metric; Optimal Alignment; measures on a graph; unbalanced measures; graph structure; Sobolev constraint; gradient flow; cu

项目成果

Dynamic Flows on Curved Space Generated by Labeled Data

• DOI: 10.48550/arxiv.2302.00061
• 发表时间: 2023-01
• 作者: Xinru Hua;Truyen V. Nguyen;Tam Le;J. Blanchet;Viet Anh Nguyen

Sobolev Transport

索博列夫运输

LSMI-Sinkhorn: Semi-supervised Squared-Loss Mutual Information Estimation with Optimal Transport

• 发表时间: 2019-09
• 期刊: ArXiv
• 作者: Yanbin Liu;M. Yamada;Yao-Hung Hubert Tsai;Tam Le;R. Salakhutdinov;Yezhou Yang

LSMI-Sinkhorn

LSMI-辛克霍恩

Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics

• 发表时间: 2022-02
• 期刊: ArXiv
• 作者: Tam Le;Truyen V. Nguyen;Dinh Q. Phung;Viet Anh Nguyen