A dynamical-system approach to mathematical programming
Optimization and Control
2017-06-09 v3
Abstract
We explore how to build a vector field from the various functions involved in a given mathematical program, and show that locally-stable equilibria of the underlying dynamical system are precisely the local solutions of the optimization problem. The general situation in which explicit inequality constraints are present is especially interesting as the vector field has to be discontinuous, and so one is led to consider discontinuous dynamical systems and their equilibria.
Cite
@article{arxiv.1401.2280,
title = {A dynamical-system approach to mathematical programming},
author = {Pablo Pedregal},
journal= {arXiv preprint arXiv:1401.2280},
year = {2017}
}
Comments
13 pages