摘要
针对传统高斯分布估计算法(Gaussian estimation of distribution algorithms,GEDAs)中变量方差减小速度快、概率密度椭球体(Probability density ellipsoid,PDE)的长轴与目标函数的改进方向相垂直,从而导致算法搜索效率低、容易早熟收敛这一问题,提出一种基于一般二阶混合矩的高斯分布估计算法.该算法利用加权的优秀样本预估高斯均值,并根据沿目标函数的改进方向偏移后的均值来估计协方差矩阵.理论和数值分析表明,这一简单操作可以在不增大算法计算量的前提下自适应地调整概率密度椭球体的位置、大小和长轴方向,提高算法的搜索效率.在14个标准函数上对所提算法进行了测试,由统计出的Cohen's d效应量指标可知该算法的全局寻优能力强于传统高斯分布估计算法;与当前先进的粒子群算法、差分进化算法相比,所提算法可以在相同的函数评价次数内获得9个函数的显著优解.
Traditional Gaussian estimation of distribution algorithms（GEDAs） are confronted with issues that variable variances decrease fast and the long axis of the probability density ellipsoid（PDE） tends to be perpendicular to the improvement direction of the objective function, leading to reduction of search efficiency of GEDA and premature convergence. To alleviate these issues, this paper proposes a novel GEDA based on the general second-order mixed moment. In each iteration, this algorithm first estimates an initial mean using weighted excellent samples, then shifts the mean along the improvement direction of the objective function and estimates the covariance matrix with the new mean as the center.Theoretical and numerical analysis results both show that this simple operation can adaptively adjust the location, size and long axis direction of PDE without increasing computation. As a consequence, the search efficiency of the algorithm is improved. Experiments are conducted on 14 benchmark functions. The resultant Cohen＇s d effect size demonstrates that the proposed algorithm possesses stronger global optimization ability than traditional GEDA. And compared with some state-of-the-art particle swarm optimization and differential evolution algorithms, it can produce significantly superior solutions for 9 functions within the same function evaluation times.
作者
任志刚
梁永胜
张爱民
庞蓓
REN Zhi-Gang;LIANG Yong-Sheng;ZHANG Ai-Min;PANG Bei(Department of Automation Science and Technology, School of Electronic and Information Engineering, Xi＇an Jiaotong University, Xi＇an 710049)
出处
《自动化学报》
EI
CSCD
北大核心
2018年第4期635-645,共11页
Acta Automatica Sinica
基金
国家自然科学基金(61105126)
中国博士后科学基金(2014M560784
2016T90922)资助~~
关键词
高斯分布估计算法
概率密度椭球体
早熟收敛
协方差矩阵
Gaussian estimation of distribution algorithm （GEDA）, probability density ellipsoid （PDE）, prematureconvergence, covariance matrix
