English

Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples

Neural and Evolutionary Computing 2024-04-09 v1 Machine Learning

Abstract

The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajectories obtained from running a solver as input have shown promise. However, it is unclear to what extent these trajectories reliably discriminate between solvers. We propose a meta approach to generating discriminatory trajectories with respect to a portfolio of solvers. The algorithm-configuration tool irace is used to tune the parameters of a simple Simulated Annealing algorithm (SA) to produce trajectories that maximise the performance metrics of ML models trained on this data. We show that when the trajectories obtained from the tuned SA algorithm are used in ML models for algorithm-selection and performance prediction, we obtain significantly improved performance metrics compared to models trained both on raw trajectory data and on exploratory landscape features.

Keywords

Cite

@article{arxiv.2404.05359,
  title  = {Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples},
  author = {Quentin Renau and Emma Hart},
  journal= {arXiv preprint arXiv:2404.05359},
  year   = {2024}
}

Comments

To appear in the proceedings of The Genetic and Evolutionary Computation Conference 2024

R2 v1 2026-06-28T15:47:17.751Z