A machine learning based algorithm selection method to solve the minimum cost flow problem

arXiv2210.02195MaRDI QIDQ6412959FDOQ6412959

Authors: Philipp Herrmann, Anna Meyer, Stefan Ruzika, Luca E. Schäfer, Fabian von der Warth 

Publication date: 3 October 2022

Abstract: The minimum cost flow problem is one of the most studied network optimization problems and appears in numerous applications. Some efficient algorithms exist for this problem, which are freely available in the form of libraries or software packages. It is noticeable that none of these solvers is better than the other solution methods on all instances. Thus, the question arises whether the fastest algorithm can be selected for a given instance based on the characteristics of the instance. To this end, we train several machine learning classifiers to predict the fastest among a given set of solvers. We accomplish this by creating a representative data set of 81,000 instances and characterizing each of these instances by a vector of relevant features. To achieve better performance, we conduct a grid search to optimize the hyperparameters of the classifiers. Finally, we evaluate the different classifiers by means of accuracy. It is shown that tree-based models appear to adapt and exploit the relevant structures of the minimum-cost flow problem particularly well on a large number of instances, predicting the fastest solver with an accuracy of more than 90%.

Has companion code repository: https://github.com/fabianvdw/mcf_alg_selection

This page was built for publication: A machine learning based algorithm selection method to solve the minimum cost flow problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6412959)