Direct and indirect operator learning strategies for parametric optimal control problems
Abstract
This paper focuses on the use of learning nonlinear operators via Deep Operator Networks (DeepONets) for approximating the solutions of optimal control problems. We study two operator learning strategies, namely, indirect and direct, both based on DeepONets, for parametric families of optimal control problems where the same problem must be solved many times for different initial data, different parameters, different cost function weights, and different bounds defining the set of the admissible controls. In the indirect strategy two DeepONets approximate the solution operators of the state and adjoint systems, and their predictions are used inside iterative projected gradient algorithms for finding the optimal control. In the direct strategy, a single DeepONet approximates the operator that maps directly to the optimal control generated by a reference solver; consequently, a new control is obtained through a single evaluation of the network. In order to analyze the computational cost, the efficiency, the speed and the accuracy of the learning strategies, we consider an optimal control problem related to an ordinary differential system that describes the temporal evolution of the glioblastoma growth subject to therapeutic interventions. For this specific optimal control problem we propose a discretize-then-optimize strategy, based on an implicit-explicit finite difference method, and then, we develop several numerical experiments in order to compare the two DeepONet learning strategies for this problem. The proposed operator learning DeepONet strategies can be adapted to approximate large classes of optimal control problems related to diverse differential systems.
Related
- Multiresolution Sobolev Trained Fourier Neural Operator for Cross-Resolution Surrogate Modelling of Parametric Two-Phase Darcy Flows in Porous Media
- Differentiating Minimal-Norm Solutions to Parametric Optimization Problems
- Variationally correct loss functions for nonlinear parametric problems and their neural approximations
- Reduced order model for parametric Boltzmann equation and its application to inverse problems
- A new operator splitting method for coupled PDE problems, with an application to poromechanics
BibTeX
@misc{forerohernandez2026direct,
title = {{Direct and indirect operator learning strategies for parametric optimal control problems}},
author = {Juan J. Forero-Hernández and Francisco Guillén-González and Élder J. Villamizar-Roa},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41532},
eprint = {2610.41532},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41532},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Direct and indirect operator learning strategies for parametric optimal control problems
AU - Juan J. Forero-Hernández
AU - Francisco Guillén-González
AU - Élder J. Villamizar-Roa
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41532
UR - https://arxiv.org/abs/2610.41532
AB - This paper focuses on the use of learning nonlinear operators via Deep Operator Networks (DeepONets) for approximating the solutions of optimal control problems. We study two operator learning strategies, namely, indirect and direct, both based on DeepONets, for parametric families of optimal control problems where the same problem must be solved many times for different initial data, different parameters, different cost function weights, and different bounds defining the set of the admissible controls. In the indirect strategy two DeepONets approximate the solution operators of the state and adjoint systems, and their predictions are used inside iterative projected gradient algorithms for finding the optimal control. In the direct strategy, a single DeepONet approximates the operator that maps directly to the optimal control generated by a reference solver; consequently, a new control is obtained through a single evaluation of the network. In order to analyze the computational cost, the efficiency, the speed and the accuracy of the learning strategies, we consider an optimal control problem related to an ordinary differential system that describes the temporal evolution of the glioblastoma growth subject to therapeutic interventions. For this specific optimal control problem we propose a discretize-then-optimize strategy, based on an implicit-explicit finite difference method, and then, we develop several numerical experiments in order to compare the two DeepONet learning strategies for this problem. The proposed operator learning DeepONet strategies can be adapted to approximate large classes of optimal control problems related to diverse differential systems.
ER -