基于泛函网络求解随机优化问题的EM算法

Electromagnetism-like mechanism algorithm for solving stochastic optimization problems based on function network

研究了一类带有随机变量的不确定优化问题。为了解决这类随机优化问题,首先用随机仿真为泛函网络产生训练样本,用泛函网络逼近随机函数的均值,将随机函数的均值转为不含随机变量的确定性函数,然后用类电磁算法求解确定性函数的最优解。最后,给出一些数值例子验证了所提算法的有效性。

This paper investigates a kind of uncertainty optimization problems with stochastic variables.First it uses stochastic simulation to generate training samples, then uses function networks to construct a deterministic function to approximate the expected value of an uncertain function. At last,electromagnetism-like mechanism （EM） algorithm is used to optimize the deterministic function. In the end of this paper, some numerical examples are presented to illustrate the effectiveness of the proposed algorithm.