Constructive interpolation and generalization rates for neural ODEs: a control perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Álvarez-López, Antonio, Liverani, Lorenzo, Zuazua, Enrique
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911735108075520
author Álvarez-López, Antonio
Liverani, Lorenzo
Zuazua, Enrique
author_facet Álvarez-López, Antonio
Liverani, Lorenzo
Zuazua, Enrique
contents We study supervised regression with neural ODEs (NODEs) from a control-theoretic perspective to derive explicit population-risk bounds. We focus on a widely used class of non-autonomous models with constant parameters and explicit time dependence, which we call semi-autonomous NODEs (SA-NODEs). We constructively prove that SA-NODEs are capable of \emph{exact} interpolation of admissible finite datasets, and even satisfy a stronger property that we call \emph{simultaneous cell controllability} (SCC): their flows can map prescribed disjoint cells into arbitrarily small target balls. This property is the mechanism that upgrades interpolation into quantitative generalization, by allowing SA-NODEs to emulate piecewise-constant nonparametric estimators. Consequently, our risk bounds recover the rates of histogram and nearest-neighbor estimators, provided the network width satisfies a conservative scaling with the sample size. Numerical experiments show that trained SA-NODEs achieve competitive -- often lower -- test errors than these baselines. Finally, we show that the explicit time dependence is essential. Although two-layer autonomous NODEs can interpolate geometrically nondegenerate datasets, structural obstructions prevent them from achieving SCC. These limitations, further confirmed numerically, support the view that SA-NODEs provide a minimal effective architecture for learning.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00469
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Constructive interpolation and generalization rates for neural ODEs: a control perspective
Álvarez-López, Antonio
Liverani, Lorenzo
Zuazua, Enrique
Optimization and Control
Machine Learning
68T07, 93B05, 62G08, 34H05, 68Q32
We study supervised regression with neural ODEs (NODEs) from a control-theoretic perspective to derive explicit population-risk bounds. We focus on a widely used class of non-autonomous models with constant parameters and explicit time dependence, which we call semi-autonomous NODEs (SA-NODEs). We constructively prove that SA-NODEs are capable of \emph{exact} interpolation of admissible finite datasets, and even satisfy a stronger property that we call \emph{simultaneous cell controllability} (SCC): their flows can map prescribed disjoint cells into arbitrarily small target balls. This property is the mechanism that upgrades interpolation into quantitative generalization, by allowing SA-NODEs to emulate piecewise-constant nonparametric estimators. Consequently, our risk bounds recover the rates of histogram and nearest-neighbor estimators, provided the network width satisfies a conservative scaling with the sample size. Numerical experiments show that trained SA-NODEs achieve competitive -- often lower -- test errors than these baselines. Finally, we show that the explicit time dependence is essential. Although two-layer autonomous NODEs can interpolate geometrically nondegenerate datasets, structural obstructions prevent them from achieving SCC. These limitations, further confirmed numerically, support the view that SA-NODEs provide a minimal effective architecture for learning.
title Constructive interpolation and generalization rates for neural ODEs: a control perspective
topic Optimization and Control
Machine Learning
68T07, 93B05, 62G08, 34H05, 68Q32
url https://arxiv.org/abs/2606.00469