EUVIMEDEUVIMED entdecken
Crossref

A Multi-Stage Metaheuristic Framework for Reliable WGAN-GP Hyperparameter Optimization

Emre Mert Dübüş, Yusuf Sönmez, Hamdi Tolga Kahraman

Advances in Artificial Intelligence Research · 21.06.2026 · 6

DOI: 10.54569/aair.1960245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Artificial Intelligence Research, online erschienen am 21.06.2026. Verfasst von Emre Mert Dübüş und 2 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) improve adversarial training stability, but performance remains highly sensitive to hyperparameters governing generator–critic balance, learning rates, optimizer momentum, regularization, and update frequency. This study presents a progressive three-stage metaheuristic framework for WGAN-GP hyperparameter optimization. Stage 1 performs low-cost preliminary exploration on MNIST. Stage 2 refines the FFHQ 64 × 64 search space using a baseline and LSHADE-cnEpSin. Stage 3 compares Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Differential Evolution (DE), and LSHADE-cnEpSin under equal function-evaluation budgets with real Fréchet Inception Distance (FID) as the primary metric. The main result is a search-validation gap: PSO achieves the best short-horizon search-phase FID, whereas GA achieves the best long-horizon final-validation FID. GA is therefore interpreted as showing delayed exploitation in the reported setting, not universal superiority. LSHADE-cnEpSin obtains the lowest search-phase mean FID and stable candidate-level behavior, showing that population-level consistency and final best-candidate quality are distinct evaluation dimensions. These results support staged, fair-budget validation as a more reliable protocol for WGAN-GP hyperparameter optimization.

Zitieren

APA

Dübüş, E. M., Sönmez, Y., & Kahraman, H. T. (2026). A Multi-Stage Metaheuristic Framework for Reliable WGAN-GP Hyperparameter Optimization. Advances in Artificial Intelligence Research, 6. https://doi.org/10.54569/aair.1960245

Vancouver

Dübüş EM, Sönmez Y, Kahraman HT. A Multi-Stage Metaheuristic Framework for Reliable WGAN-GP Hyperparameter Optimization. Advances in Artificial Intelligence Research. 2026;6. doi:10.54569/aair.1960245

BibTeX
@article{Db2026,
  author = {Dübüş, Emre Mert and Sönmez, Yusuf and Kahraman, Hamdi Tolga},
  title = {A Multi-Stage Metaheuristic Framework for Reliable WGAN-GP Hyperparameter Optimization},
  journal = {Advances in Artificial Intelligence Research},
  year = {2026},
  volume = {6},
  doi = {10.54569/aair.1960245}
}
Kostenlos starten →