On the Convergence of Irregular Sampling in Reproducing Kernel Hilbert Spaces
By: Armin Iske
Potential Business Impact:
Makes computer learning better with less data.
We analyse the convergence of sampling algorithms for functions in reproducing kernel Hilbert spaces (RKHS). To this end, we discuss approximation properties of kernel regression under minimalistic assumptions on both the kernel and the input data. We first prove error estimates in the kernel's RKHS norm. This leads us to new results concerning uniform convergence of kernel regression on compact domains. For Lipschitz continuous and H\"older continuous kernels, we prove convergence rates.
Similar Papers
Irregular Sampling of High-Dimensional Functions in Reproducing Kernel Hilbert Spaces
Machine Learning (CS)
Makes complex math problems easier to solve.
General reproducing properties in RKHS with application to derivative and integral operators
Statistics Theory
Helps computers learn from data with function values.
Convergent Methods for Koopman Operators on Reproducing Kernel Hilbert Spaces
Numerical Analysis
Makes predicting complex systems faster and more accurate.