Differential Evolution with Estimation of Distribution for Worst-Case Scenario Optimization

Antoniou, Margarita; Papa, Gregor

doi:10.3390/math9172137

Cited by 3 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, modeling p(x) directly is one of primary branches, e.g., Estimation of Distribution Algorithms (EDAs) (Hauschild and Pelikan 2011), which have achieved considerable advances (Liang et al 2020;De Bonet, Isbell, and Viola 1996;Chen et al 2017). They have potentials to capture complex structures and learn accurate distribution of promising solutions without much attention on landscape details (Cheng et al 2018;Antoniou and Papa 2021).…”

Section: Introductionmentioning

confidence: 99%

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution

Ning

Liu

et al. 2023

AAAI

View full text Add to dashboard Cite

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies to balance exploration-exploitation trade-off. It has potential to better adapt to the regularity and structure of diversified landscapes than other methods with fixed prior, e.g., Gaussian assumption or separability. Experiments on diverse BBO benchmarks and high dimensional real world applications exhibit that OPT-GAN outperforms other traditional and neural net-based BBO algorithms. The code and Appendix are available at https://github.com/NBICLAB/OPT-GAN

show abstract

Section: Introductionmentioning

confidence: 99%

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution

Ning

Liu

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…A min-max Differential Evolution (DE) is proposed in [18] with many improvements to the original DE, designed specially for minmax problems. Another nested approach was presented in [5], where a DE with an estimation of distribution algorithm is proposed and a priori knowledge of the previous generations is utilized to reduce the computational expense.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Parallel Hierarchical Differential Evolution for Min-Max Optimization Problems Using SciPy

Antoniou

Papa

2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

When optimization is applied in real-world applications, optimal solutions that do not take into account uncertainty are of limited value, since changes or disturbances in the input data may reduce the quality of the solution. One way to find a robust solution and consider uncertainty is to formulate the problem as a min-max optimization problem. Min-max optimization aims to identify solutions which remain feasible and of good quality under even the worst possible scenarios, i.e., realizations of the uncertain data, formulating a nested problem. Employing hierarchical evolutionary algorithms to solve the problem requires numerous function evaluations. Nevertheless, Evolutionary Algorithms can be easily parallelized. This work investigates a parallel model for differential evolution using SciPy, to solve general unconstrained min-max problems. A differential evolution is applied for both the design and scenario space optimization. To reduce the computational cost, the design level optimization is parallelized. The performance of the algorithm is evaluated for a different number of cores and different dimensionality of four benchmark test functions. The results show that, when the right parameters of the algorithm are selected, the parallelization can be of high benefit to a nested differential evolution.

show abstract

Soft computing technique with maintenance and controlling for distributed energy using differential evolution based local power distribution system and fuzzy radial basis function neural network

Manikandan

Chillakuru²,

Kumar³

et al. 2022

Sustainable Computing: Informatics and Systems

View full text Add to dashboard Cite

Differential Evolution with Estimation of Distribution for Worst-Case Scenario Optimization

Cited by 3 publications

References 26 publications

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution

Evaluation of Parallel Hierarchical Differential Evolution for Min-Max Optimization Problems Using SciPy

Soft computing technique with maintenance and controlling for distributed energy using differential evolution based local power distribution system and fuzzy radial basis function neural network

Contact Info

Product

Resources

About