Optimization over Trained Neural Networks: Going Large with Gradient-Based Algorithms

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tong, Jiatai, Zhu, Yilin, Serra, Thiago, Burer, Samuel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910056941879296
author Tong, Jiatai
Zhu, Yilin
Serra, Thiago
Burer, Samuel
author_facet Tong, Jiatai
Zhu, Yilin
Serra, Thiago
Burer, Samuel
contents When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local search that exploits the neural-network structure has been employed to find good solutions within a reasonable time limit. For such methods, a lower per-iteration cost is advantageous when solving larger models. The contribution of this paper is two-fold. First, we propose a gradient-based algorithm with lower per-iteration cost than existing methods. Second, we further adapt this algorithm to exploit the piecewise-linear structure of neural networks that use Rectified Linear Units (ReLUs). In line with prior research, our methods become competitive with -- and then dominant over -- other local search methods as the optimization models become larger.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24295
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimization over Trained Neural Networks: Going Large with Gradient-Based Algorithms
Tong, Jiatai
Zhu, Yilin
Serra, Thiago
Burer, Samuel
Optimization and Control
When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local search that exploits the neural-network structure has been employed to find good solutions within a reasonable time limit. For such methods, a lower per-iteration cost is advantageous when solving larger models. The contribution of this paper is two-fold. First, we propose a gradient-based algorithm with lower per-iteration cost than existing methods. Second, we further adapt this algorithm to exploit the piecewise-linear structure of neural networks that use Rectified Linear Units (ReLUs). In line with prior research, our methods become competitive with -- and then dominant over -- other local search methods as the optimization models become larger.
title Optimization over Trained Neural Networks: Going Large with Gradient-Based Algorithms
topic Optimization and Control
url https://arxiv.org/abs/2512.24295