Randomized methods for computing optimal transport without regularization and their convergence analysis

• Main Authors: Xie, Yue, Wang, Zhongjian, Zhang, Zhiwen
• 其他作者: School of Physical and Mathematical Sciences
• 格式: Article
• 語言: English
• 出版: 2024
• 主題: Mathematical Sciences; Optimal transport; Deep particle method
• 在線閱讀: https://hdl.handle.net/10356/178997
• 機構: Nanyang Technological University

The optimal transport (OT) problem can be reduced to a linear programming (LP) problem through discretization. In this paper, we introduced the random block coordinate descent (RBCD) methods to directly solve this LP problem. Our approach involves restricting the potentially large-scale optimization...