arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.13653stat.MLcs.LG
收藏

具有含噪树度量的测度最优传输

Optimal Transport for Measures with Noisy Tree Metric

The Institute of Statistical Mathematics(统计数学研究所);The University of Akron(阿克伦大学);RIKEN AIP(理化学研究所人工智能项目)

Tam Le, Truyen Nguyen, Kenji Fukumizu

AI总结:

针对含噪或对抗扰动树结构下的最优传输问题,提出基于边删除/添加的树度量不确定性集,证明鲁棒OT具有闭式解、度量性与负定性,并据此构造正定核用于文档分类和拓扑数据分析。

摘要:

我们研究支撑在树度量空间上的概率测度的最优传输(OT)问题。已知此类OT问题(即tree-Wasserstein,TW)具有闭式表达式,但从根本上依赖于输入测度支撑集上的底层树结构。然而在实践中,由于含噪或对抗性测量,给定的树结构可能受到扰动。为缓解这一问题,我们采用极大极小鲁棒OT方法,该方法考虑两个输入测度在树度量不确定性集合上的最大可能距离。一般而言,由于其非凸性和非光滑性,这种方法即使对于支撑在一维空间上的测度也难以计算,这阻碍了其实际应用,尤其是在大规模场景中。在本工作中,我们从边删除/添加的视角提出了新颖的树度量不确定性集合,在一个简洁框架中涵盖了多样化的树结构。因此,基于所提出的不确定性集合,并利用支撑集上的树结构,我们证明鲁棒OT与其对应的标准OT(即TW)一样,也具有可快速计算的闭式表达式。此外,我们证明鲁棒OT满足度量性质并且是负定的。随后,我们利用其负定性提出正定核,并在多个真实世界数据集上的若干模拟中对其进行测试,应用于文档分类和拓扑数据分析。

英文摘要:

We study optimal transport (OT) problem for probability measures supported on a tree metric space. It is known that such OT problem (i.e., tree-Wasserstein (TW)) admits a closed-form expression, but depends fundamentally on the underlying tree structure over supports of input measures. In practice, the given tree structure may be, however, perturbed due to noisy or adversarial measurements. To mitigate this issue, we follow the max-min robust OT approach which considers the maximal possible distances between two input measures over an uncertainty set of tree metrics. In general, this approach is hard to compute, even for measures supported in one-dimensional space, due to its non-convexity and non-smoothness which hinders its practical applications, especially for large-scale settings. In this work, we propose novel uncertainty sets of tree metrics from the lens of edge deletion/addition which covers a diversity of tree structures in an elegant framework. Consequently, by building upon the proposed uncertainty sets, and leveraging the tree structure over supports, we show that the robust OT also admits a closed-form expression for a fast computation as its counterpart standard OT (i.e., TW). Furthermore, we demonstrate that the robust OT satisfies the metric property and is negative definite. We then exploit its negative definiteness to propose positive definite kernels and test them in several simulations on various real-world datasets on document classification and topological data analysis.

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。

↑