期刊
SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE
卷 1, 期 2, 页码 313-332出版社
SIAM PUBLICATIONS
DOI: 10.1137/18M1216134
关键词
t-SNE; visualization; spectral clustering; discrete dynamical system; discrete elliptic equation; maximum principle
资金
- NIH [1R01HG008383-01A1]
- U.S. NIH MSTP Training grant [T32GM007205]
- Institute of New Economic Thinking [INO15-00038]
t-distributed stochastic neighborhood embedding (t-SNE), a clustering and visualization method proposed by van der Maaten and Hinton in 2008, has rapidly become a standard tool in a number of natural sciences. Despite its overwhelming success, there is a distinct lack of mathematical foundations, and the inner workings of the algorithm are not well understood. The purpose of this paper is to prove that t-SNE is able to recover well-separated clusters; more precisely, we prove that t-SNE in the early exaggeration phase, an optimization technique proposed by van der Maaten and Hinton [J. Mach. Learn. Res., 9 (2008), pp. 2579-2605] and van der Maaten [J. Mach. Learn. Res., 15 (2014), pp. 3221-3245], can be rigorously analyzed. As a byproduct, the proof suggests novel ways for setting the exaggeration parameter alpha and step size h. Numerical examples illustrate the effectiveness of these rules: in particular, the quality of embedding of topological structures (e.g., the swiss roll) improves. We also discuss a connection to spectral clustering methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据