stat.MLNov 6, 2026

Kernel-Based Learning of Analytic Operators and Parametric PDEs

Authors: Giovanni S. Alberti, Markus Holzleitner, Lorenzo Rosasco, Matteo Santacesaria

Organizations: MaLGa Center, DIMA, University of Genoa, Via Dodecaneso 35, 16146 Genoa, Italy · Institute for Machine Learning, Johannes Kepler University Linz, Altenberger Straße 69, 4040 Linz, Austria · MaLGa Center, DIBRIS, University of Genoa, Via Dodecaneso 35, 16146 Genoa, Italy

Abstract

We study kernel-based learning of analytic operators from finite samples, with a focus on how the regularity of the target should determine the choice of the kernel. We establish embeddings of analytic operators into vector-valued reproducing kernel Hilbert spaces and derive finite-sample, high-probability guarantees that quantify the uncertainty due to random sampling: in the noiseless setting, suitable analytic kernels yield rates exponential in a fractional power of the sample size, while Sobolev-type kernels yield polynomial rates. We apply the theory to the solution operator of a parametric elliptic PDE, where the training data are themselves finite-element approximations, and obtain bounds that separate the sampling and discretization contributions to the error and prescribe how the mesh size should be coupled to the sample size. The results are illustrated numerically.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Kernel-based Operator Learning: Error Analysis, Budget Allocation, and a Physics-Informed Extension

    Jul 7, 2026Rüdiger KempfKernel MethodsPDE Operator Learning

  2. Near-Optimal Learning of Gaussian Sobolev Operators

    Jul 8, 2026Ben Adcock, Michael Griebel, Gregor MaierRecursive Least SquaresOperator Learning

  3. Kernel Methods for Learning Operators with Multiple Inputs and Outputs

    Aug 12, 2026Adrien Weihs, Chunyang Liao, Jingmin Sun +1Kernel MethodsPDE Operator Learning