Finite-dimensional approximations of push-forwards on locally analytic functionals

arXiv:2404.10769v4 Announce Type: replace-cross 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.

Related

• Resistance Distance and Linearized Optimal Transport on Graphs
• Neural Operator: Is data all you need to model the world? An insight into the paradigm of data-driven scientific ML
• Learning the Riccati solution operator for time-varying LQR via Deep Operator Networks
• Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis

Source: arXiv cs.LG | 2026-04-22