Controlling mutation/selection algorithms with stochastic approximation

摘要: The article describes a stochastic approximation method to deal with adaptation in the mutation/selection strategy. Small mutation probabilities are considered. First, convergence rate of population Markov chain toward equilibrium is given. This result allows control number generations sufficient reach stationary probability distribution. Under stationarity, algorithm proceeds parameter called radius. main issue initialization process. gives rule initialize this process for simple one-dimensional problems. guarantees both scheme, and that an accurate solution produced.