Mathematics – Statistics Theory
Scientific paper
2010-09-29
Mathematics
Statistics Theory
to appear in Neural Information Processing Systems 2010
Scientific paper
We prove rates of convergence in the statistical sense for kernel-based least squares regression using a conjugate gradient algorithm, where regularization against overfitting is obtained by early stopping. This method is directly related to Kernel Partial Least Squares, a regression method that combines supervised dimensionality reduction with least squares projection. The rates depend on two key quantities: first, on the regularity of the target regression function and second, on the intrinsic dimensionality of the data mapped into the kernel space. Lower bounds on attainable rates depending on these two quantities were established in earlier literature, and we obtain upper bounds for the considered method that match these lower bounds (up to a log factor) if the true regression function belongs to the reproducing kernel Hilbert space. If this assumption is not fulfilled, we obtain similar convergence rates provided additional unlabeled data are available. The order of the learning rates match state-of-the-art results that were recently obtained for least squares support vector machines and for linear regularization operators.
Blanchard Gilles
Kraemer Nicole
No associations
LandOfFree
Optimal learning rates for Kernel Conjugate Gradient regression does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Optimal learning rates for Kernel Conjugate Gradient regression, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal learning rates for Kernel Conjugate Gradient regression will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-523386