Nonlinear Optimization with GPU-Accelerated Neural Network Constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911309117784064 |
|---|---|
| author | Parker, Robert Dowson, Oscar LoGiudice, Nicole Garcia, Manuel Bent, Russell |
| author_facet | Parker, Robert Dowson, Oscar LoGiudice, Nicole Garcia, Manuel Bent, Russell |
| contents | We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gray box" where intermediate variables and constraints are not exposed to the optimization solver. Compared to the full-space formulation, in which intermediate variables and constraints are exposed to the optimization solver, the reduced-space formulation leads to faster solves and fewer iterations in an interior point method. We demonstrate the benefits of this method on two optimization problems: Adversarial generation for a classifier trained on MNIST images and security-constrained optimal power flow with transient feasibility enforced using a neural network surrogate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22462 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nonlinear Optimization with GPU-Accelerated Neural Network Constraints Parker, Robert Dowson, Oscar LoGiudice, Nicole Garcia, Manuel Bent, Russell Machine Learning We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gray box" where intermediate variables and constraints are not exposed to the optimization solver. Compared to the full-space formulation, in which intermediate variables and constraints are exposed to the optimization solver, the reduced-space formulation leads to faster solves and fewer iterations in an interior point method. We demonstrate the benefits of this method on two optimization problems: Adversarial generation for a classifier trained on MNIST images and security-constrained optimal power flow with transient feasibility enforced using a neural network surrogate. |
| title | Nonlinear Optimization with GPU-Accelerated Neural Network Constraints |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.22462 |