Automated Configuration of Genetic Algorithms by Tuning for Anytime Performance

Ye, Furong; Doerr, Carola; Wang, Hao; Bäck, Thomas

doi:10.1109/tevc.2022.3159087

Cited by 12 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in some cases it can be desirable to find a set of diverse, well-performing solutions to the AC problem. For example, previous studies [21,30] found that algorithm configurators can obtain different results when tuning for different objectives (i.e., expected running time, best-found fitness, and anytime performance), which suggests that a bi-or multi-objective approach to algorithm configuration can be a promising research direction. For such multi-objective configuration tasks, having diverse populations of configurations is a necessity to understand the Pareto front.…”

Section: Definition 1 (Algorithm Configuration Problem)mentioning

confidence: 99%

“…2, 4, and 5 for results of the obtained configurations. Recall that AC techniques have been applied in [30] for exploring promising configurations of the GA on diverse problems. Apart from analyzing a single optimal configuration, such benchmarking studies can also benefit from diverse configurations to investigate algorithms' performance with specific parameter settings.…”

Section: Benefits From Diverse Configurationsmentioning

confidence: 99%

“…Therefore, we investigate alternative selection mechanisms which take into account the diversity of the selected elite configurations. In addition, the observations from [30] inspire a discussion on searching for various competitive configurations with different patterns, which is addressed by our discussion that more knowledge can be obtained by searching diverse configurations.…”

Section: Introductionmentioning

confidence: 99%

“…Premature convergence is a common problem for optimization methods resulting in being trapped into local optima, which can also present irace from finding the optimal configurations. For example, irace fails to find the optimal configuration of a family of genetic algorithms (GAs) for OneMax in [30]. There exists more than one type of competitive configuration of the GA for OneMax, which is known due to the extensive body of theoretical work [11,28].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Non-elitist Selection Can Improve the Performance of Irace

Vermetten

Doerr

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Modern optimization strategies such as evolutionary algorithms, ant colony algorithms, Bayesian optimization techniques, etc. come with several parameters that steer their behavior during the optimization process. To obtain high-performing algorithm instances, automated algorithm configuration techniques have been developed. One of the most popular tools is irace, which evaluates configurations in sequential races, making use of iterated statistical tests to discard poorly performing configurations. At the end of the race, a set of elite configurations are selected from those survivor configurations that were not discarded, using greedy truncation selection. We study two alternative selection methods: one keeps the best survivor and selects the remaining configurations uniformly at random from the set of survivors, while the other applies entropy to maximize the diversity of the elites. These methods are tested for tuning ant colony optimization algorithms for traveling salesperson problems and the quadratic assignment problem and tuning an exact tree search solver for satisfiability problems. The experimental results show improvement on the tested benchmarks compared to the default selection of irace. In addition, the obtained results indicate that non-elitist can obtain diverse algorithm configurations, which encourages us to explore a wider range of solutions to understand the behavior of algorithms.

show abstract

Section: Definition 1 (Algorithm Configuration Problem)mentioning

confidence: 99%

Section: Benefits From Diverse Configurationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Non-elitist Selection Can Improve the Performance of Irace

Vermetten

Doerr

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The logger is integrated into a wide range of existing tools for benchmarking, including problem suites such as PBO (Doerr et al, 2020) and the W-model (Weise et al, 2020) for discrete optimization and COCO's BBOB (Hansen et al, 2021) for the continuous case. On the algorithm side, IOHexperimenter has been connected to several modular algorithm frameworks, such as modular GA (Ye et al, 2021) and modular CMA-ES (de Nobel et al, 2021). Additionally, output generated by the included loggers is compatible with the IOHanalyzer module (Wang et al, 2020) for interactive performance analysis.…”

Section: Functionalitymentioning

confidence: 99%

IOHexperimenter: Benchmarking Platform for Iterative Optimization Heuristics

Nobel¹,

Ye²,

Vermetten³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present IOHexperimenter, the experimentation module of the IOHprofiler project, which aims at providing an easy-to-use and highly customizable toolbox for benchmarking iterative optimization heuristics such as evolutionary and genetic algorithms, local search algorithms, Bayesian optimization techniques, etc. IOHexperimenter can be used as a stand-alone tool or as part of a benchmarking pipeline that uses other components of IOHprofiler such as IOHanalyzer, the module for interactive performance analysis and visualization. IOHexperimenter provides an efficient interface between optimization problems and their solvers while allowing for granular logging of the optimization process. These logs are fully compatible with existing tools for interactive data analysis, which significantly speeds up the deployment of a benchmarking pipeline. The main components of IOHexperimenter are the environment to build customized problem suites and the various logging options that allow users to steer the granularity of the data records.

show abstract