将Wasserstein空间的大子集嵌入Banach空间
Embedding large subsets of Wasserstein spaces into Banach spaces
- Université Paris-Saclay(巴黎萨克雷大学)
- CNRS(法国国家科学研究中心)
- Inria(法国研究与数字联盟)
- Laboratoire de mathématiques d’Orsay(奥赛数学实验室)
- École normale supérieure(巴黎高等师范学院)
- Université PSL(巴黎文理研究大学)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
本研究证明三种经典嵌入在带矩界的Wasserstein空间子集上为双Hölder映射,其结果与完整Wasserstein空间嵌入非平凡型Banach空间的已知阻碍形成对比,还明确了结论成立所需矩的尖锐性。
AI中文摘要:
将Wasserstein空间的子集嵌入线性空间是兼具理论与计算意义的问题。本研究证明,Wasserstein空间到非平凡型Banach空间的三种经典且自然的嵌入,在由矩界给定的Wasserstein空间子集上是双Hölder的。这些嵌入在多个应用中被使用,分别是线性化最优传输嵌入、sliced-Wasserstein嵌入以及一种特定的核均值嵌入。我们的结果与将完整Wasserstein空间嵌入非平凡型Banach空间的已知阻碍形成对比,还展示了我们结论成立所需矩的尖锐性。
英文摘要:
Embedding subsets of Wasserstein spaces into linear spaces is a problem of both theoretical and computational interest. In this work, we prove that three classical and natural embeddings of Wasserstein spaces into Banach spaces of non-trivial type are bi-Hölder on subsets of Wasserstein spaces given by moment bounds. These embeddings, all considered in multiple applications, are the linearized optimal transport embedding, the sliced-Wasserstein embedding, and a particular kernel mean embedding. Our results contrast with known obstructions to embeddin the full Wasserstein space into Banach spaces of non-trivial type. We also show the sharpness of our results regarding the moments required for our conclusions to hold.