论文标题
黑盒优化的生成进化策略
Generative Evolutionary Strategy For Black-Box Optimizations
论文作者
论文摘要
许多科学和技术问题与优化有关。其中，高维空间中的黑盒优化尤其具有挑战性。最近的基于神经网络的黑盒优化研究表明了值得注意的成就。但是，它们在高维搜索空间中的能力仍然有限。这项研究提出了一种基于进化策略（ES）和生成神经网络（GNN）模型的黑盒优化方法。我们设计了算法，以使ES和GNN模型合作起作用。该混合模型可以对替代网络的可靠培训；它优化了多目标，高维和随机黑盒功能。我们的方法优于本实验中的基线优化方法，包括ES和贝叶斯优化。
Many scientific and technological problems are related to optimization. Among them, black-box optimization in high-dimensional space is particularly challenging. Recent neural network-based black-box optimization studies have shown noteworthy achievements. However, their capability in high-dimensional search space is still limited. This study proposes a black-box optimization method based on the evolution strategy (ES) and the generative neural network (GNN) model. We designed the algorithm so that the ES and the GNN model work cooperatively. This hybrid model enables reliable training of surrogate networks; it optimizes multi-objective, high-dimensional, and stochastic black-box functions. Our method outperforms baseline optimization methods in this experiment, including ES, and Bayesian optimization.
