It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces. Consequently, many tools of machine learning were extended to such spaces, but only few discrepancies to compare probability distributions defined over those spaces exist. Among the possible candidates, optimal transport distances are well defined on such Riemannian manifolds and enjoy strong theoretical properties, but suffer from high computational cost. On Euclidean spaces, sliced-Wasserstein distances, which leverage a closed-form of the Wasserstein distance in one dimension, are more computationally efficient, but are not readily available on hyperbolic spaces. In this work, we propose to derive novel hyperbolic sliced-Wasserstein discrepancies. These constructions use projections on the underlying geodesics either along horospheres or geodesics. We study and compare them on different tasks where hyperbolic representations are relevant, such as sampling or image classification.
翻译:它被证明有益于许多类型的数据,这些类型的数据代表着一种内在的等级结构,可以嵌入双曲空间。因此,许多机器学习工具都扩展到了这些空间,但用于比较这些空间所定义的概率分布的差别很小。在可能的候选者中,最理想的迁移距离在里曼尼多元体上定义得很明确,并具有很强的理论特性,但具有很高的计算成本。在利用瓦塞斯坦距离的封闭式一个维塞尔斯坦距离的欧西里德空间,切片-瓦瑟斯坦长距离,在计算上效率更高,但在双曲空间上却不易找到。在这项工作中,我们提议得出新的超曲切片-瓦瑟斯坦差。这些建筑在沿日光层或地德等地缘上使用对基本大地测地学的预测。我们研究并比较与超偏度表相关的不同任务,例如取样或图像分类。