NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001
2002

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-02-121


2002-121
Optimizing Kernel Alignment over Combinations of Kernels

Jaz Kandola
John Shawe-Taylor
Nello Cristianini

ABSTRACT
Alignment has recently been proposed as a method for measuring the degree of agreement between a kernel and a learning task \cite{cris2001}. Previous approaches to optimizing kernel alignment have required the eigendecomposition of the kernel matrix which can be computationally prohibitive especially for large kernel matrices. In this paper we propose a general method for optimizing alignment over a linear combination of kernels. We apply the approach to give both transductive and inductive algorithms based on the Incomplete Cholesky factorization of the kernel matrix. The Incomplete Cholesky factorization is equivalent to performing a Gram-Schmidt orthogonalization of the training points in the feature space. The alignment optimization method adapts the feature space to increase its training set alignment. Regularization is required to ensure this alignment is also retained for the test set. Both theoretical and experimental evidence is given to show that improving the alignment leads to a reduction in generalization error of standard classifiers.

Download Postscript