Landmark diffusion maps (L-dMaps): Accelerated manifold learning out-of-sample extension
Landmark diffusion maps (L-dMaps): Accelerated manifold learning out-of-sample extension
复制标题
DOI：
10.1016/j.acha.2017.08.004
复制
发表时间：
2019-07-01
影响因子：
2.5
通讯作者：
Ferguson, Andrew L.
中科院分区：
文献类型：
--
作者：
Long, Andrew W.;Ferguson, Andrew L.
扩散映射是一种基于对数据上的扩散过程进行调和分析的非线性流形学习技术。具有计算复杂度为$O(N)$（其中$N$是构成流形的点数）的样本外扩展，阻碍了其在需要快速嵌入高维数据流的在线学习应用中的应用。我们提出地标扩散映射（L - dMaps）将复杂度降低到$O(M)$，其中$M$（此处句子不完整）
Diffusion maps are a nonlinear manifold learning technique based on harmonic analysis of a diffusion process over the data. Out-of-sample extensions with computational complexity (9(N), where N is the number of points comprising the manifold, frustrate applications to online learning applications requiring rapid embedding of high-dimensional data streams. We propose landmark diffusion maps (L-dMaps) to reduce the complexity to O(M), where M