A reformulation to Embedding a Neural Network in a linear program without integer variables
Year: 2024
Type: preprint
Abstract: In this technical report, a new formulation for embedding a neural network into an optimization model is described. This formulation does not require binary variables to properly compute the output of the neural network for specific types of problems. Preliminary experiments show that this reformulation resulted in faster computation times when solving a proposed showcase model, in which non-linearity is necessary to be computed. This is in comparison with the classic formulation and off-the-shelf tools of commercial solvers.
Source: arXiv (Cornell University)
Authors: -de-Alba, Héctor G., Tellez, Andres, Santos, Cipriano, Gómez, Emmanuel
Institution: Tecnológico de Monterrey
Language: English
Subfield: Numerical Analysis
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391590718