


























Abstract: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.
| Comments: | Accepted at Learning for Dynamics and Control Conference (L4DC) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2511.13174 [cs.LG] |
| (or arXiv:2511.13174v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2511.13174 arXiv-issued DOI via DataCite |
From: Ella Johanna Schmidtobreick [view email]
[v1]
Mon, 17 Nov 2025 09:22:45 UTC (918 KB)
[v2]
Tue, 19 May 2026 15:40:58 UTC (760 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。