Saved in:
Bibliographic Details
Main Authors: Schmidtobreick, Ella J., Arnström, Daniel, Häusner, Paul, Sjölund, Jens
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.13174
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914579834994688
author Schmidtobreick, Ella J.
Arnström, Daniel
Häusner, Paul
Sjölund, Jens
author_facet Schmidtobreick, Ella J.
Arnström, Daniel
Häusner, Paul
Sjölund, Jens
contents Quadratic programming (QP) solvers are widely used in real-time control and optimization, but their computational cost often limits applicability in time-critical settings. To resolve this, we propose a learning-to-optimize approach using graph neural networks (GNNs) to predict active constraints in the dual active-set solver DAQP. Our method exploits the structural properties of QPs by representing them as bipartite graphs and learns to approximate the optimal active set for effectively warm-starting the solver. Across varying problem sizes, the GNN consistently reduces the number of solver iterations compared to cold-starting, while performance is comparable to a multilayer perceptron baseline. In contrast to the baseline, our GNN-based approach trained on varying problem sizes generalizes to unseen dimensions, demonstrating flexibility and scalability. These results highlight the potential of structure-aware learning to accelerate optimization in real-time applications such as model predictive control.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13174
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Warm-starting active-set solvers using graph neural networks
Schmidtobreick, Ella J.
Arnström, Daniel
Häusner, Paul
Sjölund, Jens
Machine Learning
Quadratic programming (QP) solvers are widely used in real-time control and optimization, but their computational cost often limits applicability in time-critical settings. To resolve this, we propose a learning-to-optimize approach using graph neural networks (GNNs) to predict active constraints in the dual active-set solver DAQP. Our method exploits the structural properties of QPs by representing them as bipartite graphs and learns to approximate the optimal active set for effectively warm-starting the solver. Across varying problem sizes, the GNN consistently reduces the number of solver iterations compared to cold-starting, while performance is comparable to a multilayer perceptron baseline. In contrast to the baseline, our GNN-based approach trained on varying problem sizes generalizes to unseen dimensions, demonstrating flexibility and scalability. These results highlight the potential of structure-aware learning to accelerate optimization in real-time applications such as model predictive control.
title Warm-starting active-set solvers using graph neural networks
topic Machine Learning
url https://arxiv.org/abs/2511.13174