EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming

Yu Liu, Fabricio Oliveira, Jan Kronqvist

EURO Journal on Computational Optimization · 2026 · 14 · 100141

DOI: 10.1016/j.ejco.2026.100141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift EURO Journal on Computational Optimization, 2026. Verfasst von Yu Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Two-stage stochastic programming (2SP) offers a basic framework for modelling decision-making under uncertainty, yet scalability remains a challenge due to the computational complexity of recourse function evaluation. Existing learning-based methods like Neural Two-Stage Stochastic Programming (Neur2SP) employ neural networks (NNs) as recourse function surrogates but rely on computationally intensive mixed-integer programming (MIP) formulations. We propose ICNN-enhanced 2SP, a method that leverages Input Convex Neural Networks (ICNNs) to exploit linear programming (LP) representability in convex 2SP problems. By architecturally enforcing convexity and enabling exact inference through LP, our approach eliminates the need for integer variables inherent in the conventional MIP-based formulation while retaining an exact embedding of the ICNN surrogate within the 2SP framework. This results in a more computationally efficient alternative, and we show that good solution quality can be maintained. Comprehensive experiments reveal that ICNNs incur only marginally longer training times while achieving validation accuracy on par with their standard NN counterparts. Across benchmark problems, ICNN-enhanced 2SP often exhibits considerably faster solution times than the MIP-based formulations while preserving solution quality, with these advantages becoming significantly more pronounced as problem scale increases. For the most challenging instances, the method achieves speedups of up to 100$\times$ with solution quality superior to MIP-based formulations.

Förderung

  • China Scholarship Council

Zitieren

APA

Liu, Y., Oliveira, F., & Kronqvist, J. (2026). ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming. EURO Journal on Computational Optimization, 14, 100141. https://doi.org/10.1016/j.ejco.2026.100141

Vancouver

Liu Y, Oliveira F, Kronqvist J. ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming. EURO Journal on Computational Optimization. 2026;14:100141. doi:10.1016/j.ejco.2026.100141

BibTeX
@article{Liu2026,
  author = {Liu, Yu and Oliveira, Fabricio and Kronqvist, Jan},
  title = {ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming},
  journal = {EURO Journal on Computational Optimization},
  year = {2026},
  volume = {14},
  pages = {100141},
  doi = {10.1016/j.ejco.2026.100141}
}
Kostenlos starten →