Convexity and strict convexity for compositional neural networks in high-dimensional optimal control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grüne, Lars, Kleinberg, Konrad, Kruse, Thomas, Sperl, Mario
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915604591542272
author Grüne, Lars
Kleinberg, Konrad
Kruse, Thomas
Sperl, Mario
author_facet Grüne, Lars
Kleinberg, Konrad
Kruse, Thomas
Sperl, Mario
contents Neural networks (NNs) have emerged as powerful tools for solving high-dimensional optimal control problems. In particular, their compositional structure has been shown to enable efficient approximation of high-dimensional functions, helping to mitigate the curse of dimensionality in optimal control problems. In this work, we build upon the theoretical framework developed by Kang & Gong (SIAM J. Control Optim. 60(2):786-813, 2022), particularly their results on NN approximations for compositional functions in optimal control. Theorem 6.2 in Kang & Gong (SIAM J. Control Optim. 60(2):786-813, 2022) establishes that, under suitable assumptions on the compositional structure and its associated features, optimal control problems with strictly convex cost functionals admit a curse-of-dimensionality-free approximation of the optimal control by NNs. We extend this result in two directions. First, we analyze the strict convexity requirement on the cost functional and demonstrate that reformulating a discrete-time optimal control problem with linear transitions and stage costs as a terminal cost problem ensures the necessary strict convexity. Second, we establish a generalization of Theorem 6.2 in Kang & Gong (SIAM J. Control Optim. 60(2):786-813, 2022) which provides weak error bounds for optimal control approximations by NNs when the cost functional is only convex rather than strictly convex.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05339
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convexity and strict convexity for compositional neural networks in high-dimensional optimal control
Grüne, Lars
Kleinberg, Konrad
Kruse, Thomas
Sperl, Mario
Optimization and Control
68T07, 49M99
Neural networks (NNs) have emerged as powerful tools for solving high-dimensional optimal control problems. In particular, their compositional structure has been shown to enable efficient approximation of high-dimensional functions, helping to mitigate the curse of dimensionality in optimal control problems. In this work, we build upon the theoretical framework developed by Kang & Gong (SIAM J. Control Optim. 60(2):786-813, 2022), particularly their results on NN approximations for compositional functions in optimal control. Theorem 6.2 in Kang & Gong (SIAM J. Control Optim. 60(2):786-813, 2022) establishes that, under suitable assumptions on the compositional structure and its associated features, optimal control problems with strictly convex cost functionals admit a curse-of-dimensionality-free approximation of the optimal control by NNs. We extend this result in two directions. First, we analyze the strict convexity requirement on the cost functional and demonstrate that reformulating a discrete-time optimal control problem with linear transitions and stage costs as a terminal cost problem ensures the necessary strict convexity. Second, we establish a generalization of Theorem 6.2 in Kang & Gong (SIAM J. Control Optim. 60(2):786-813, 2022) which provides weak error bounds for optimal control approximations by NNs when the cost functional is only convex rather than strictly convex.
title Convexity and strict convexity for compositional neural networks in high-dimensional optimal control
topic Optimization and Control
68T07, 49M99
url https://arxiv.org/abs/2511.05339