Manifold Learning: The Price of Normalization

Details Manifold Learning: The Price of Normalization Manifold Learning: The Price of Normalization

2008-06-16

arxiv.org/abs/0806.2646v1

Statistics

Machine Learning

Submitted to JMLR

Scientific paper

We analyze the performance of a class of manifold-learning algorithms that find their output by minimizing a quadratic form under some normalization constraints. This class consists of Locally Linear Embedding (LLE), Laplacian Eigenmap, Local Tangent Space Alignment (LTSA), Hessian Eigenmaps (HLLE), and Diffusion maps. We present and prove conditions on the manifold that are necessary for the success of the algorithms. Both the finite sample case and the limit case are analyzed. We show that there are simple manifolds in which the necessary conditions are violated, and hence the algorithms cannot recover the underlying manifolds. Finally, we present numerical results that demonstrate our claims.

Affiliated with

Also associated with

No associations

Rating

Manifold Learning: The Price of Normalization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Manifold Learning: The Price of Normalization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Manifold Learning: The Price of Normalization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-92504