mlsanityData to 7 Oct 2026

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

arXiv 2606.00469 ↗First posted 30 May 2026math.OC stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

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 exact interpolation of admissible finite datasets, and even satisfy a stronger property that we call 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 59 references that are in the map. First posted on arXiv 30 May 2026.

Builds on

35 of 59 references.

References · 35

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  3. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  4. 2019Benign Overfitting in Linear Regressioncited by 544
  5. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  6. 2019Augmented Neural ODEscited by 396
  7. 2017Stable Architectures for Deep Neural Networkscited by 340
  8. 2014Breaking the Curse of Dimensionality with Convex Neural Networkscited by 329
  9. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  10. 2020Dissecting Neural ODEscited by 150
  11. 2016Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with ℓ1 and ℓ0 Controlscited by 84
  12. 2019Deep Learning via Dynamical Systems: An Approximation Perspectivecited by 78
23 more
  1. 2017Maximum Principle Based Algorithms for Deep Learningcited by 77
  2. 2018A Mean-Field Optimal Control Formulation of Deep Learningcited by 67
  3. 2021Neural ODE control for classification, approximation and transportcited by 56
  4. 2020Structure preserving deep learningcited by 30
  5. 2019Deep neural networks, generic universal interpolation, and controlled ODEscited by 28
  6. 2023Distribution learning via neural differential equations: a nonparametric statistical perspectivecited by 22
  7. 2023Generalization bounds for neural ordinary differential equations and deep residual networkscited by 21
  8. 2023Interpolation, Approximation and Controllability of Deep Neural Networkscited by 15
  9. 2020Large-time asymptotics in deep learningcited by 14
  10. 2019Control in the spaces of ensembles of pointscited by 8
  11. 2022Neural ODE Control for Trajectory Approximation of Continuity Equationcited by 8
  12. 2022Deep Neural Network Approximation of Invariant Functions through Dynamical Systemscited by 8
  13. 2023Control of neural transport for normalizing flowscited by 8
  14. 2024Interplay between depth and width for interpolation in neural ODEscited by 8
  15. 2024Feedback Favors the Generalization of Neural ODEscited by 8
  16. 2020Time Dependence in Non-Autonomous Neural ODEscited by 7
  17. 2021Deep Learning Approximation of Diffeomorphisms via Linear-Control Systemscited by 7
  18. 2021Interpolation and approximation via Momentum ResNets and Neural ODEscited by 4
  19. 2023Cluster-based classification with neural ODEs via controlcited by 4
  20. 2024Constructive approximate transport maps with normalizing flowscited by 4
  21. 2023On the Generalization and Approximation Capacities of Neural Controlled Differential Equationscited by 3
  22. 2023From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networkscited by 3
  23. 2024Minimax problems for ensembles of control-affine systemscited by 1

Built on by

Not cited yet.