基于Lévy分布的柔软自适应演化采样算法

Evolutionary sampling approach with soft adaptive Lévy probability distribution

已经有相关工作将演化思想引入采样算法中,并结合Lévy分布提出了自适应的采样算法。针对Lévy分布的参数设置和厚尾特性的关系进行了研究,改进了基于Lévy分布的演化采样算法,通过设置该分布的参数α值为1.0、1.3、1.7、2.0,分别对应四种转移概率分布,从而增加了生成的候选样本的多样性。理论分析和实验表明,改进算法在收敛速率和精度上优于基于高斯分布、柯西分布,对称指数分布的演化采样算法和其他自适应的演化采样算法。

Some research introduced evolution idea into sampling algorithms, and proposed related algorithms combined with adaptive Lévy distribution. This paper improved the evolutionary sampling algorithm based on Lévy distribution. By setting the parameter α of this distribution to 1.0, 1.3, 1.7, 2.0, corresponding to the four transition probability distributions, it increased the diversity of the generated candidate samples. Theoretical analysis and experimental results show that the proposed algorithm is superior to the evolutionary sampling algorithm based on Gaussian distribution, Cauchy distribution, symmetrical exponential distribution and other adaptive evolutionary sampling algorithms in terms of convergence rate and accuracy.