基于遗传算法的最小一乘回归新算法

A New Algorithm for the Least Absolute Deviation Regression Based on the Genetic Algorithm

最小一乘在稳健性上比最小二乘好,使得最小一乘在工程中得到广泛的应用,但求解最小一乘的算法并不理想;本文根据最小一乘的性质,把最小一乘问题变为组合优化问题。将遗传算法用在最小一乘模型的求解上,在后面的仿真实验中得到了较好的效果。

The least absolute deviations are using widely used in engineering because of it's robustness,but the algorithm solving the least absolute deviation is not efficient. Changing the least absolute deviation to the combinatorial optimization,based on it's characters, we use the genetic algorithm to solve the least absolute deviation regression. At last the numerical experimentations show that the Genetic algorithm is efficient.