Metraipolis › archive › dc_5157dbcafaa2

Learning to Solve Mixed-Integer Nonlinear Programming with Neural Networks and Sequential Quadratic Programming Refinement — arXiv:2610.05746

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.05746
License (as archived)
CC0-1.0
Archived
2026-10-06T13:06:12.867Z
SHA-256 of the archived text
09a71f5092d6d378097b18dd3dc68d059258e87b994a94897e575b8008c8dd3c
Stable URL of this page
https://metraipolis.com/documento/dc_5157dbcafaa2

How to cite

Learning to Solve Mixed-Integer Nonlinear Programming with Neural Networks and Sequential Quadratic Programming Refinement — arXiv:2610.05746 — arXiv (en), https://arxiv.org/abs/2610.05746 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5157dbcafaa2 (Metraipolis archive dc_5157dbcafaa2, sha256 09a71f5092d6d378097b18dd3dc68d059258e87b994a94897e575b8008c8dd3c)
BibTeX
@misc{dc5157dbcafaa2,
  title = {Learning to Solve Mixed-Integer Nonlinear Programming with Neural Networks and Sequential Quadratic Programming Refinement — arXiv:2610.05746},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.05746},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5157dbcafaa2; sha256 09a71f5092d6d378097b18dd3dc68d059258e87b994a94897e575b8008c8dd3c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.05746. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a learning-to-optimize framework for solving parametric mixed-integer nonlinear programs arising in model predictive control and trajectory optimization. The proposed method combines neural network prediction with a sequential quadratic programming (SQP) refinement layer. First, neural networks are trained using a combination of supervised and self-supervised losses to predict integer solutions together with compatible continuous warm starts. To account for prediction inaccuracies, the trained predictor generates multiple candidate integer solutions, each paired with a continuous initialization. The integer solutions are then fixed, and a differentiable SQP layer refines the associated continuous variables over a prescribed number of iterations. The SQP-layer parameters, including the curvature regularization and step size, are trained to improve both feasibility and objective value after every iteration. By separating integer prediction from continuous optimization-based refinement, the proposed framework improves robustness to imperfect neural predictions while maintaining a predictable computational budget. We demonstrate the proposed framework on contact and trajectory optimization for a planar box-pushing example.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.05746 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T11:21:31.913Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).