Abstract:Relocation of compact sets in an $n$-dimensional manifold by self-diffeomorphism is of its own interest as well as significant potential applications to data classification in data science. This paper presents a theory for relocating a finite number of compact sets in $\mathbb{R}^n$ to be relocated to arbitrary target domains in $\mathbb{R}^n$ by diffeomorphisms of $\mathbb{R}^n$. Furthermore, we prove that for any such collection, there exists a differentiable embedding into $\mathbb{R}^{n+1}$ such that their images become linearly separable.
As applications of the established theory, we show that a finite number of compact datasets in $\mathbb{R}^n$ can be made linearly separable by width-$n$ deep neural networks (DNNs) with Leaky-ReLU, ELU, or SELU activation functions, under a mild condition. In addition, we show that any finite number of mutually disjoint compact datasets in $\mathbb{R}^n$ can be made linearly separable in $\mathbb{R}^{n+1}$ by a width-$(n+1)$ DNN.
| Subjects: | Machine Learning (cs.LG) |
| MSC classes: | 57R50, 68T07 |
| Cite as: | arXiv:2604.21393 [cs.LG] |
| (or arXiv:2604.21393v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.21393 arXiv-issued DOI via DataCite (pending registration) |
From: Xiao-Song Yang [view email]
[v1]
Thu, 23 Apr 2026 08:00:55 UTC (660 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。