距离和损失函数约束正则化的AdaBoost算法

AdaBoost algorithm based on distance and loss function constraint regularization

基于距离函数和损失函数正则化的权值更新模式,使用相关熵距离函数,Itakura-Saito距离函数,指数一次近似距离和相关熵损失函数结合,实现了三种AdaBoost弱分类器权值更新算法。使用UCI数据库数据对提出的三种算法AdaBoostRE,AdaBoostIE,AdaBoostEE与Real AdaBoost,Gentle AdaBoost和Modest AdaBoost算法作了比较,可以看到提出的AdaBoostRE算法预测效果最好,优于Real AdaBoost,Gentle AdaBoost和Modest AdaBoost算法。

According to weight update model via distance and lost function regularization, proposed by J.Kivinen and M.K.Warmuth, using relative entropy, Itakura-Saito, first order exponential approximation distance function, combined with relative entropy lost function, this paper devises three sorts of weight update method of weak classifier of AdaBoost. Using the UCI real datasets, the three algorithms AdaBoostRE, AdaBoostlE, AdaBoostEE are compared with three leading assembly classifier： Real AdaBoost, Gentle AdaBoost and Modest AdaBoost. Experimental results show promising performance of the proposed method.