Finite-dimensional approximations of push-forwards on locally analytic functionals
Abstract
This paper develops a functional-analytic framework for approximating the push-forward induced by an analytic map from finitely many samples. Instead of working directly with the map, we study the push-forward on the space of locally analytic functionals and identify it, via the Fourier--Borel transform, with an operator on the space of entire functions of exponential type. This yields finite-dimensional approximations of the push-forward together with explicit error bounds expressed in terms of the smallest eigenvalues of certain Hankel moment matrices. Moreover, we obtain sample complexity bounds for the approximation from i.i.d.~sampled data. As a consequence, we show that linear algebraic operations on the finite-dimensional approximations can be used to reconstruct analytic vector fields from discrete trajectory data. In particular, we prove convergence of a data-driven method for recovering the vector field of an ordinary differential equation from finite-time flow map data under fairly general conditions.
Cite
@article{arxiv.2404.10769,
title = {Finite-dimensional approximations of push-forwards on locally analytic functionals},
author = {Isao Ishikawa},
journal= {arXiv preprint arXiv:2404.10769},
year = {2026}
}
Comments
Revised version. Removed one auxiliary lemma, corrected finite-dimensional matrix conventions and the Hermitian moment-matrix formulation, revised the statements and estimates in the push-forward approximation, analytic-map reconstruction/least-squares approximation, and vector-field reconstruction results, and fixed references and typographical errors