On Manifold Regularization

Mikhail Belkin; Partha Niyogi; Vikas Sindhwani. 20 June, 2004.
Communicated by Partha Niyogi.


We propose a family of learning algorithms based on a new form of regularization which allows us to incoporate both labeled and unlabeled data in a general-purpose learner. Transductive graph learning algorithms and standard methods including SVM and Regularized Least Squares can be obtained as special cases of our framework.

Original Document

The original document is available in PDF (uploaded 20 June, 2004 by Partha Niyogi).