English

Fast operator learning for mapping correlations

Numerical Analysis 2025-12-22 v2 Numerical Analysis

Abstract

We propose a fast, optimization-free method for learning the transition operators of high-dimensional Markov processes. The central idea is to perform a Galerkin projection of the transition operator to a suitable set of low-order bases that capture the correlations between the dimensions. Such a discretized operator can be obtained from moments corresponding to our choice of basis without curse of dimensionality. Furthermore, by exploiting its low-rank structure and the spatial decay of correlations, we can obtain a compressed representation with computational complexity of order O(dN)\mathcal{O}(dN), where dd is the dimensionality and NN is the sample size. We further theoretically analyze the approximation error of the proposed compressed representation. We numerically demonstrate that the learned operator allows efficient prediction of future events and solving high-dimensional boundary value problems. This gives rise to a simple linear algebraic method for high-dimensional rare-events simulations.

Keywords

Cite

@article{arxiv.2512.09286,
  title  = {Fast operator learning for mapping correlations},
  author = {Yuehaw Khoo and Yuguan Wang and Siyao Yang},
  journal= {arXiv preprint arXiv:2512.09286},
  year   = {2025}
}

Comments

9 figures

R2 v1 2026-07-01T08:18:16.993Z