Comparing parameter tuning methods for evolutionary algorithms

By Selmar K. Smit, Agoston E. Eiben. IEEE Congress on Evolutionary Computation, 2009

316 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/e55f07832ea45b90293e1f29f40b2705d6e02b87

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Swagatam Das
2. Ponnuthurai Nagaratnam Suganthan
3. Seyedali Mirjalili
4. Xin-She Yang
5. Francisco Herrera
6. Carlos Artemio Coello Coello
7. Seyed Mohammad Mirjalili
8. Xin Yao

In Computational Theory and Mathematics

1. Swagatam Das
2. Ponnuthurai Nagaratnam Suganthan
3. Xin-She Yang
4. Seyedali Mirjalili
5. Carlos Artemio Coello Coello
6. Xin Yao
7. Seyed Mohammad Mirjalili
8. Agoston E. Eiben

Citations in the corpus

• Resampling Methods for Meta-Model Validation with Recommendations for Evolutionary Computation (2012, background): “It should also be taken into account that the ability to interpret a meta-model is often seen as an important benefit that other optimization techniques lack (e.g., see Smit and Eiben, 2009).”
• Parameter tuning for configuring and analyzing evolutionary algorithms (2011, methodology): “In a comparative study it has been shown that SPO is able to find high quality parameter vectors comparable to the ones found by meta-evolutionary algorithms [25].”
• Bio-inspired computation: Where we stand and what's next (2019, methodology): “Unfortunately, it is often the case that bio-inspired algorithms have too many parameters, so that seeking the best value for each one of them can be regarded as another optimization problem by itself [296].”
• A Survey of Automatic Parameter Tuning Methods for Metaheuristics (2020, methodology): “In a meta-EA, its individuals, i.e., numeric vectors, represent parameter config-urations and the performance measures established by evaluation method (such as repeated evaluation or F -Race) of each configuration are related to the corresponding (meta-) fitness [48].”
• A Hybrid Genetic Algorithm for Multidepot and Periodic Vehicle Routing Problems (2012, methodology): “In order to identify good parameter values, we adopted the metacalibration approach (Mercer and Sampson 1978), which was shown to perform particularly well for genetic algorithm calibration (Smit and Eiben 2009).”