arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.13630cs.LGcs.ITmath.IT
收藏

最优运输的小批量估计的预算约束界

Budget-Constrained Bounds for Mini-Batch Estimation of Optimal Transport

Microsoft Research(微软研究院);Amazon(亚马逊)

David Alvarez-Melis, Nicolò Fusi, Lester Mackey, Tal Wagner

摘要:

最优传输(OT)是比较概率分布的基本工具,但其精确计算对于大型数据集仍然是禁止的。在这项工作中,我们引入了新的家庭的上界和下界的OT问题的聚合解决方案的小批量OT问题。上限家庭包含传统的小批量平均在一个极端和一个紧密的界限,发现最佳耦合的小批量在其他。在这些极端之间,我们提出了各种方法来构建边界的基础上一个固定的计算预算。通过各种实验,我们探索了计算预算和边界紧密性之间的权衡,并显示了这些边界在计算机视觉应用中的有用性。

英文摘要:

Optimal Transport (OT) is a fundamental tool for comparing probability distributions, but its exact computation remains prohibitive for large datasets. In this work, we introduce novel families of upper and lower bounds for the OT problem constructed by aggregating solutions of mini-batch OT problems. The upper bound family contains traditional mini-batch averaging at one extreme and a tight bound found by optimal coupling of mini-batches at the other. In between these extremes, we propose various methods to construct bounds based on a fixed computational budget. Through various experiments, we explore the trade-off between computational budget and bound tightness and show the usefulness of these bounds in computer vision applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑