对不可比空间上的最优迁移的贡献
A contribution to Optimal Transport on incomparable spaces
摘要:
最优运输是一种理论,它允许定义概率分布之间距离的几何概念,并找到点集之间的对应关系。许多机器学习应用都是从这个理论衍生出来的,处于数学和优化的前沿。本文提出研究不同数据属于不可比空间的复杂场景。特别是,我们解决以下问题:如何定义和应用最优传输之间的图形,结构化数据?当数据变化而不是嵌入在相同的度量空间中时,它如何适应?本文针对这些不同的情况提出了一套最优运输工具。一个重要的部分是特别致力于研究格罗莫夫-瓦瑟斯坦距离,其性质允许定义有趣的运输问题上的不可比空间。更广泛地说,我们分析的数学特性的各种建议的工具,我们建立算法的解决方案来计算它们,我们研究它们的适用性,在许多机器学习的覆盖,特别是分类,简化,分区的结构化数据,以及异构域适应。
英文摘要:
Optimal Transport is a theory that allows to define geometrical notions of distance between probability distributions and to find correspondences, relationships, between sets of points. Many machine learning applications are derived from this theory, at the frontier between mathematics and optimization. This thesis proposes to study the complex scenario in which the different data belong to incomparable spaces. In particular we address the following questions: how to define and apply Optimal Transport between graphs, between structured data? How can it be adapted when the data are varied and not embedded in the same metric space? This thesis proposes a set of Optimal Transport tools for these different cases. An important part is notably devoted to the study of the Gromov-Wasserstein distance whose properties allow to define interesting transport problems on incomparable spaces. More broadly, we analyze the mathematical properties of the various proposed tools, we establish algorithmic solutions to compute them and we study their applicability in numerous machine learning scenarii which cover, in particular, classification, simplification, partitioning of structured data, as well as heterogeneous domain adaptation.
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。