English

Large Data Limits of Laplace Learning for Gaussian Measure Data in Infinite Dimensions

Machine Learning 2026-01-22 v1 Machine Learning Numerical Analysis Numerical Analysis

Abstract

Laplace learning is a semi-supervised method, a solution for finding missing labels from a partially labeled dataset utilizing the geometry given by the unlabeled data points. The method minimizes a Dirichlet energy defined on a (discrete) graph constructed from the full dataset. In finite dimensions the asymptotics in the large (unlabeled) data limit are well understood with convergence from the graph setting to a continuum Sobolev semi-norm weighted by the Lebesgue density of the data-generating measure. The lack of the Lebesgue measure on infinite-dimensional spaces requires rethinking the analysis if the data aren't finite-dimensional. In this paper we make a first step in this direction by analyzing the setting when the data are generated by a Gaussian measure on a Hilbert space and proving pointwise convergence of the graph Dirichlet energy.

Keywords

Cite

@article{arxiv.2601.14515,
  title  = {Large Data Limits of Laplace Learning for Gaussian Measure Data in Infinite Dimensions},
  author = {Zhengang Zhong and Yury Korolev and Matthew Thorpe},
  journal= {arXiv preprint arXiv:2601.14515},
  year   = {2026}
}