arXiv:2604.13295cs.LGmath.PR2026-04
揭示 t-SNE 在降维中丢失数据关键特征的理论局限
Some Theoretical Limitations of t-SNE

- 构建数学框架分析 t-SNE 的信息损失机制
- 证明在多种场景下重要数据特征会显著丢失
- 为可视化降维提供理论警示,适合研究者参考
t-SNE 作为一种流行的降维技术,尤其适用于数据可视化。众所周知,所有降维方法都可能导致数据重要特征的丢失。本文通过建立一套数学框架,在不同场景下得出若干结果,系统揭示了 t-SNE 在降维过程中如何丢失数据的关键特征。
原文摘要 · Abstract (English)
t-SNE has gained popularity as a dimension reduction technique, especially for visualizing data. It is well-known that all dimension reduction techniques may lose important features of the data. We provide a mathematical framework for understanding this loss for t-SNE by establishing a number of results in different scenarios showing how important features of data are lost by using t-SNE.
降维可视化理论分析
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。