Convergence rate of the data-independent $P$-greedy algorithm in kernel-based approximation
Provides theoretical justification for a practical greedy point-selection algorithm in kernel-based approximation, confirming a conjecture from the original paper.
The paper proves the convergence rate of the data-independent P-greedy algorithm for kernel-based approximation, showing it is near-optimal for kernels generating Sobolev spaces and that selected points are asymptotically uniformly distributed.
Kernel-based methods provide flexible and accurate algorithms for the reconstruction of functions from meshless samples. A major question in the use of such methods is the influence of the samples locations on the behavior of the approximation, and feasible optimal strategies are not known for general problems. Nevertheless, efficient and greedy point-selection strategies are known. This paper gives a proof of the convergence rate of the data-independent \textit{$P$-greedy} algorithm, based on the application of the convergence theory for greedy algorithms in reduced basis methods. The resulting rate of convergence is shown to be near-optimal in the case of kernels generating Sobolev spaces. As a consequence, this convergence rate proves that, for kernels of Sobolev spaces, the points selected by the algorithm are asymptotically uniformly distributed, as conjectured in the paper where the algorithm has been introduced.