Saved in:
Bibliographic Details
Main Authors: -de-Alba, Héctor G., Tellez, Andres, Santos, Cipriano, Gómez, Emmanuel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.02086
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910317857996800
author -de-Alba, Héctor G.
Tellez, Andres
Santos, Cipriano
Gómez, Emmanuel
author_facet -de-Alba, Héctor G.
Tellez, Andres
Santos, Cipriano
Gómez, Emmanuel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02086
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A reformulation to Embedding a Neural Network in a linear program without integer variables
-de-Alba, Héctor G.
Tellez, Andres
Santos, Cipriano
Gómez, Emmanuel
Optimization and Control
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.
title A reformulation to Embedding a Neural Network in a linear program without integer variables
topic Optimization and Control
url https://arxiv.org/abs/2402.02086