English

Kantorovich--Kernel Neural Operators: Approximation Theory, Asymptotics, and Neural Network Interpretation

Machine Learning 2026-03-30 v1 Machine Learning Functional Analysis

Abstract

This paper studies a class of multivariate Kantorovich-kernel neural network operators, including the deep Kantorovich-type neural network operators studied by Sharma and Singh. We prove density results, establish quantitative convergence estimates, derive Voronovskaya-type theorems, analyze the limits of partial differential equations for deep composite operators, prove Korovkin-type theorems, and propose inversion theorems. This paper studies a class of multivariate Kantorovich-kernel neural network operators, including the deep Kantorovich-type neural network operators studied by Sharma and Singh. We prove density results, establish quantitative convergence estimates, derive Voronovskaya-type theorems, analyze the limits of partial differential equations for deep composite operators, prove Korovkin-type theorems, and propose inversion theorems. Furthermore, this paper discusses the connection between neural network architectures and the classical positive operators proposed by Chui, Hsu, He, Lorentz, and Korovkin.

Cite

@article{arxiv.2603.26418,
  title  = {Kantorovich--Kernel Neural Operators: Approximation Theory, Asymptotics, and Neural Network Interpretation},
  author = {Tian-Xiao He},
  journal= {arXiv preprint arXiv:2603.26418},
  year   = {2026}
}
R2 v1 2026-07-01T11:40:47.843Z