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.
SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples
National University of Singapore(新加坡国立大学)
我们考虑学习伊辛树模型时,从节点的观察是由独立的,但不相同分布的噪声与未知的统计损坏。Katiyar等人(2020)表明,虽然无法恢复精确的树结构,但可以恢复部分树结构;即属于包含真树的等价类的结构。本文对Katiyar et al.(2020)进行了系统的改进。首先,我们提出了一个新的不可能的结果,通过推导出的部分恢复所需的样本数的界限。第二,我们推导出一个显着改善的样本复杂度的结果,其中的最小相关$ρ_{\min}$的依赖是$ρ_{\min}^{-8}$,而不是$ρ_{\min}^{-24}$。最后,我们提出了对称几何平均(SGA),一个更强大的统计算法的部分树恢复。我们提供了各种树的误差指数分析和广泛的数值结果,以表明SGA的样本复杂度明显优于Katiyar等人的算法。SGA可以很容易地扩展到高斯模型,并通过数值实验表明,同样优越。
UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
Sungkyunkwan University(成均馆大学);IPAI (Interdisciplinary Program in Artificial Intelligence, Seoul National University)(人工智能跨学科项目(Seoul National University));Department of Mathematical Sciences, Seoul National University(首尔国立大学数学科学系)
Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));CSIRO’s Data61(联邦科学与工业研究组织数据61部门);The University of Sydney(悉尼大学);School of Artificial Intelligence, Jilin University(吉林大学人工智能学院)
Institut de Matemàtiques de la UPC-BarcelonaTech (IMTech)(加泰罗尼亚理工大学巴塞罗那技术学院数学研究所(IMTech));Universitat Politècnica de Catalunya(加泰罗尼亚理工大学);Centre de Recerca Matemàtica(数学研究中心);Universitat Pompeu Fabra(庞培法布拉大学)