PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Kernel Partial Least Squares is Universally Consistent
Gilles Blanchard and Nicole Krämer
In: AISTATS 2010, May 13-15, 2010, Sardinia, Italy.


We prove the statistical consistency of kernel Partial Least Squares Regression applied to a bounded regression learning problem on a reproducing kernel Hilbert space. Partial Least Squares stands out of well-known classical approaches as e.g. Ridge Regression or Principal Components Regression, as it is not defined as the solution of a global cost minimization procedure over a fixed model nor is it a linear estimator. Instead, approximate solutions are constructed by projections onto a nested set of data-dependent subspaces. To prove consistency, we exploit the known fact that Partial Least Squares is equivalent to the conjugate gradient algorithm in combination with early stopping. The choice of the stopping rule (number of iterations) is a crucial point. We study two empirical stopping rules. The first one monitors the estimation error in each iteration step of Partial Least Squares, and the second one estimates the empirical complexity in terms of a condition number. Both stopping rules lead to universally consistent estimators provided the kernel is universal.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Additional Information:(accepted for AISTATS 2010)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:5895
Deposited By:Gilles Blanchard
Deposited On:08 March 2010