English

Turnpike and Sparse Optimal Control for Semiautonomous Neural ODEs

Optimization and Control 2026-06-28 v1

Abstract

We study long-time optimal control of control-affine semiautonomous neural ordinary differential equations (SA-NODEs) with 1\ell^1-regularized controls. Three results are established. First, optimal state-control pairs satisfy an \emph{exponential turnpike property}: they remain exponentially close to a stationary optimal pair for most of the time horizon, with decay rate and prefactor independent of the horizon length TT. Second, 1\ell^1 penalisation induces \emph{one-sided temporal sparsity}: optimal controls are active at full amplitude on an initial arc [0,T][0,T^*] and vanish identically on (T,T)(T^*,T), where TT^* is independent of TT for TT large. Third, an integral turnpike estimate shows the time-averaged deviation from the stationary pair is bounded uniformly in TT. The proofs combine dissipativity inequalities, uniform adjoint bounds via the Pontryagin optimality system, and a time-rescaling argument adapted to the semiautonomous architecture. Numerical experiments on a Duffing oscillator and a damped pendulum confirm the three-phase turnpike profile and the one-sided sparsity structure, and demonstrate a 30×30\times parameter reduction over vanilla NODEs with no loss of stabilization performance.

Cite

@article{arxiv.2606.29343,
  title  = {Turnpike and Sparse Optimal Control for Semiautonomous Neural ODEs},
  author = {Dev Prakash Jha and Raju K. George},
  journal= {arXiv preprint arXiv:2606.29343},
  year   = {2026}
}
R2 v1 2026-07-22T20:14:32.750Z