Comparing Algorithm Selection Approaches on Black-Box Optimization Problems

Abstract

Performance complementarity of solvers available to tackle black-box optimization problems gives rise to the important task of algorithm selection (AS). Automated AS approaches can help replace tedious and labor-intensive manual selection, and have already shown promising performance in various optimization domains. Automated AS relies on machine learning (ML) techniques to recommend the best algorithm given the information about the problem instance. Unfortunately, there are no clear guidelines for choosing the most appropriate one from a variety of ML techniques. Tree-based models such as Random Forest or XGBoost have consistently demonstrated outstanding performance for automated AS. Transformers and other tabular deep learning models have also been increasingly applied in this context.

Authors 6

1. Ana Kostovska

   Jožef Stefan Institute · Jožef Stefan International Postgraduate School

   Affiliation as printed

   Jožef Stefan Institute, Ljubljana, Slovenia

2. Anja Jankovič

   Sorbonne Université

   Affiliation as printed

   Sorbonne Université, Paris, France

3. Diederick Vermetten Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, Netherlands

4. Sašo Džeroski

   Jožef Stefan Institute · Jožef Stefan International Postgraduate School

   Affiliation as printed

   Jožef Stefan Institute, Ljubljana, Slovenia

5. Tome Eftimov

   Jožef Stefan Institute · Jožef Stefan International Postgraduate School

   Affiliation as printed

   Jožef Stefan Institute, Ljubljana, Slovenia

6. Carola Doerr

   Centre National de la Recherche Scientifique · Sorbonne Université

   Affiliation as printed

   CNRS, Paris, France

   Sorbonne Université, Paris, France