Self-supervised learning of iterative solvers for constrained optimization
Results in Control and Optimization · 2026-06 · 23 · 100751
DOI: 10.1016/j.rico.2026.100751 ↗Kurz gefasst
Fachartikel in der Zeitschrift Results in Control and Optimization, 2026-06. Verfasst von Lukas Lüken und 1 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The real-time solution of parametric optimization problems is critical for applications that demand high accuracy under tight real-time constraints, such as model predictive control. To this end, this work presents a learning-based iterative solver for constrained optimization, comprising a neural network predictor that generates initial primal-dual solution estimates, followed by a learned iterative solver that refines these estimates to reach high accuracy. We introduce a novel loss function based on Karush-Kuhn-Tucker (KKT) optimality conditions, enabling fully self-supervised training without pre-solved optimizer solutions. Theoretical guarantees ensure that the training loss function attains minima exclusively at KKT points. A convexification procedure enables application to nonconvex problems while preserving these guarantees. Experiments on two nonconvex case studies demonstrate speedups of up to one order of magnitude compared to state-of-the-art solvers such as IPOPT, while achieving orders of magnitude higher accuracy than competing learning-based approaches.
Zitieren
APA
Lüken, L., & Lucia, S. (2026). Self-supervised learning of iterative solvers for constrained optimization. Results in Control and Optimization, 23, 100751. https://doi.org/10.1016/j.rico.2026.100751
Vancouver
Lüken L, Lucia S. Self-supervised learning of iterative solvers for constrained optimization. Results in Control and Optimization. 2026;23:100751. doi:10.1016/j.rico.2026.100751
BibTeX
@article{Lken2026,
author = {Lüken, Lukas and Lucia, Sergio},
title = {Self-supervised learning of iterative solvers for constrained optimization},
journal = {Results in Control and Optimization},
year = {2026},
volume = {23},
pages = {100751},
doi = {10.1016/j.rico.2026.100751}
}
EUVIMED