A gradient oriented recombination scheme for evolution strategies

This paper proposes a novel recombination scheme for evolutionary algorithms, which can guide the new population generation towards the maximum increase of the objective function. Given the current sample points and their function evaluations, the Shepard’s interpolation method is used to approximate the underlying objective function in that local region. We then compute the gradient of the estimated function which in consequence leads to an iterative process, called the mean shift, for searching the local function optimum. In each mean shift step, we calculate the weighted mean of sample points in the kernel window, followed by shifting the location of the kernel to the computed mean. Such iterative process eventually converges to the point at which the estimated objective function has zero gradient. We use the converged point as the output of our recombination operator. Experimental results show that such gradient based recombination scheme can improve the efficiency of optimizat...

• Type: Conference
• Year: 2009
• Where: SAC
• Authors: Haifeng Chen, Guofei Jiang
• Keywords: Applied Computing, Mean Shift, Objective Function, Recombination Scheme, SAC 2009