Performance Analysis of a Manifold Learning Algorithm in Dimension Reduction

@inproceedings{Huo2006PerformanceAO,
  title={Performance Analysis of a Manifold Learning Algorithm in Dimension Reduction},
  author={X. Huo and Andrew K. Smith},
  year={2006}
}
We consider the performance of local tangent space alignment (Zhang and Zha, 2004), one of several manifold learning algorithms which has been proposed as a dimension reduction method, when errors are present in the observations. Matrix perturbation theory is applied to obtain a worst-case upper bound on the deviation of the solution, which is an invariant… CONTINUE READING