In this paper we address a practical aspect of differential barrier penalty functions in linear programming. In this respect we propose an affine scaling interior point algorithm based on a large classe of differential barrier functions. The comparison of the algorithm with a vesion of the classical affine scaling algorithm shows that the algorithm is robust and efficient. We thus show that differential barrier functions open up new perspectives in linear optimization.
@article{arxiv.1705.07667,
title = {An affine scaling method using a class of differential barrier functions},
author = {Abdessamad Barbara},
journal= {arXiv preprint arXiv:1705.07667},
year = {2017}
}