General reproducing properties in RKHS with application to derivative and integral operators
By: Fatima-Zahrae El-Boukkouri, Josselin Garnier, Olivier Roustant
Potential Business Impact:
Helps computers learn from data with function values.
In this paper, we consider the reproducing property in Reproducing Kernel Hilbert Spaces (RKHS). We establish a reproducing property for the closure of the class of combinations of composition operators under minimal conditions. This allows to revisit the sufficient conditions for the reproducing property to hold for the derivative operator, as well as for the existence of the mean embedding function. These results provide a framework of application of the representer theorem for regularized learning algorithms that involve data for function values, gradients, or any other operator from the considered class.
Similar Papers
On the Convergence of Irregular Sampling in Reproducing Kernel Hilbert Spaces
Machine Learning (Stat)
Makes computer learning better with less data.
Derivative estimation by RKHS regularization for learning dynamics from time-series data
Numerical Analysis
Cleans messy data to find hidden rules.
Learning functions, operators and dynamical systems with kernels
Machine Learning (CS)
Teaches computers to learn from data.