Convergence and Rate of Convergence of a Manifold-Based Dimension Reduction Algorithm

Convergence and Rate of Convergence of a Manifold-Based Dimension Reduction Algorithm
复制标题

基于流形的降维算法的收敛性和收敛率

DOI:
--
复制
发表时间:
2008
期刊:
Neural Information Processing Systems
影响因子:
--
通讯作者:
H. Zha
H. Zha
中科院分区:
--
文献类型:
--
作者:
Andrew Smith;X. Huo;H. Zha

文献摘要

被引文献

相似文献

我们研究了局部流形学习算法LTSA[13]的收敛速度和收敛速度。主要的技术工具是对LTSA解对应的线性不变子空间进行摄动分析。我们得到了LTSA最坏情况下的误差上界,这自然会导致收敛结果。然后,我们在一种特殊情况下给出了LTSA的收敛速度。
We study the convergence and the rate of convergence of a local manifold learning algorithm: LTSA [13]. The main technical tool is the perturbation analysis on the linear invariant subspace that corresponds to the solution of LTSA. We derive a worst-case upper bound of errors for LTSA which naturally leads to a convergence result. We then derive the rate of convergence for LTSA in a special case.