English

Convergence Rates for Learning Pseudo-Differential Operators

Statistics Theory 2026-01-09 v1 Machine Learning Numerical Analysis Numerical Analysis Machine Learning Statistics Theory

Abstract

This paper establishes convergence rates for learning elliptic pseudo-differential operators, a fundamental operator class in partial differential equations and mathematical physics. In a wavelet-Galerkin framework, we formulate learning over this class as a structured infinite-dimensional regression problem with multiscale sparsity. Building on this structure, we propose a sparse, data- and computation-efficient estimator, which leverages a novel matrix compression scheme tailored to the learning task and a nested-support strategy to balance approximation and estimation errors. In addition to obtaining convergence rates for the estimator, we show that the learned operator induces an efficient and stable Galerkin solver whose numerical error matches its statistical accuracy. Our results therefore contribute to bringing together operator learning, data-driven solvers, and wavelet methods in scientific computing.

Keywords

Cite

@article{arxiv.2601.04473,
  title  = {Convergence Rates for Learning Pseudo-Differential Operators},
  author = {Jiaheng Chen and Daniel Sanz-Alonso},
  journal= {arXiv preprint arXiv:2601.04473},
  year   = {2026}
}

Comments

72 pages, 1 figure

R2 v1 2026-07-01T08:55:21.182Z