Approximation by multivariate max-product Kantorovich-type operators and learning rates of least-squares regularized regression (Q2191850)

In a recent paper, for univariate max-product sampling operators based on general kernels with bounded generalized absolute moments, the authors have obtained several \(L_\mu^p\) convergence properties on bounded intervals or on the whole real axis. In this paper, firstly the authors obtain quantitative estimates with respect to a K-functional, for the multivariate Kantorovich variant of these max-product sampling operators with the integrals written in terms of Borel probability measures. Applications of these approximation results to learning theory are obtained