Egor Kurbatov
ABSTRACT
The choice of selection operators in evolutionary algorithms can greatly affect their performance, as it can be hard to balance maintaining population diversity with providing enough selection pressure. Recently Corus et al. have shown that reverse tournaments of fixed size can be a good default choice for steady-state evolutionary algorithms.
In this paper, we aim to further explore this idea, by evaluating the (μ + 1) evolutionary algorithm with uniform, k-inverse tournament and inverse elitist selection on the problem of hard test generation for the maximum flow problem. Our results show that the performance of the k-inverse tournament is highly dependent on the problem, the choices of population size and the tournament size. In some cases, the k-inverse tournament outperforms the uniform selection operator, but similar performance can be achieved by using the uniform selection with the increased population size.
- Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. 2001. Introduction to Algorithms, 2nd Ed. MIT Press, Cambridge, Massachusetts.Google Scholar
Digital Library
- Dogan Corus, Duc-Cuong Dang, Anton V. Eremeev, and Per Kristian Lehre. 2018. Level-Based Analysis of Genetic Algorithms and Other Search Processes. IEEE Transactions on Evolutionary Computation 22, 5 (2018), 707--719.Google ScholarDigital Library
- Dogan Corus, Andrei Lissovoi, Pietro S Oliveto, and Carsten Witt. 2021. On steady-state evolutionary algorithms and selective pressure: why inverse rank-based allocation of reproductive trials is best. ACM Transactions on Evolutionary Learning and Optimization 1, 1 (2021), 1--38.Google ScholarDigital Library
- Per Kristian Lehre. 2010. Negative drift in populations. In International Conference on Parallel Problem Solving from Nature. Springer, 244--253.Google ScholarCross Ref
- Vladimir Mironovich and Maxim Buzdalov. 2015. Hard test generation for maximum flow algorithms with the fast crossover-based evolutionary algorithm. In Proceedings of Genetic and Evolutionary Computation Conference Companion. 1229--1232.Google ScholarDigital Library
- Vladimir Mironovich and Maxim Buzdalov. 2017. Evaluation of heavy-tailed mutation operator on maximum flow test generation problem. In Proceedings of Genetic and Evolutionary Computation Conference Companion. 1423--1426.Google ScholarDigital Library
Index Terms
- Evaluation of inverse selection operators on maximum flow test generation problem
Recommendations
Evaluation of heavy-tailed mutation operator on maximum flow test generation problem
GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference CompanionThe general recommendation for the mutation rate in standard-bit mutation is 1/n, which gives asymptotically optimal expected optimization times for several simple test problems. Recently, Doerr et al. have shown that such mutation rate is not ideal, ...
Hard Test Generation for Maximum Flow Algorithms with the Fast Crossover-Based Evolutionary Algorithm
GECCO Companion '15: Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary ComputationMost evolutionary algorithms not only throw out insufficiently good solutions, but forget all information they obtained from their evaluation, which reduces their speed from the information theory point of view. An evolutionary algorithm which does not ...
Measuring and Maintaining Population Diversity in Search-Based Unit Test Generation
Search-Based Software EngineeringAbstractGenetic algorithms (GAs) have been demonstrated to be effective at generating unit tests. However, GAs often suffer from a loss of population diversity, which causes the search to prematurely converge, thus negatively affecting the resulting code ...
Comments