PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A metamorphosis of Canonical Correlation Analysis into Multivariate Maximum Margin Learning
Sandor Szedmak, Tijl De Bie and David Hardoon
In: ESANN 2007, Bruges, Belgium(2007).


Canonical Correlation Analysis(CCA) is a useful tool to discover relationship between different sources of information represented by vectors. The solution of the underlying optimisation problem involves a generalised eigenproblem and is nonconvex. We will show a sequence of transformations which turn CCA into a convex maximum margin problem. The new formulation can be applied for the same class of problems at a significantly lower computational cost and with a better numerical stability.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:3825
Deposited By:Tijl De Bie
Deposited On:25 February 2008