STATISTICS SEMINAR :: Nonlinear Dimension Reduction and Applications

Primary tabs

I will present an informal discussion of several recent algorithms for nonlinear dimension reduction, both supervised and unsupervised, including Isomap, local linear embedding, Hessian-LLE, local tangent space alignment, semi-definite embedding, and contour regression. I'll try my best to highlight their differences and commonalities, and point out several topics that deserve further investigation. Connections to other areas such as semi-definite programming, mesh parameterization, surface reconstruction, and numerical solution of differential equations.


  • Workflow Status: Published
  • Created By: Barbara Christopher
  • Created: 10/08/2010
  • Modified By: Fletcher Moore
  • Modified: 10/07/2016


No keywords were submitted.

Target Audience

No target audience selected.