中文摘要：

IB方法使用源变量和相关变量的联合概率分布对源变量进行最大化压缩，使压缩变量最大化地保存相关变量的信息，连续IB算法（sIB）是一种较好的、应用较多的IB算法之一，但该算法存在效率低、优化不充分等问题．为了解决sIB在应用中存在的这些问题，提出了一种基于变异的迭代sIB算法（isIB）．isIB算法首先从相关实验中选取合理的变异率；基于该变异率，该算法从sIB算法所产生的初始解向量中随机选取相应比例的位置，对其中的类标号进行随机变异并优化；再通过多次迭代获得了相应的优化解．实验表明在数据集相同、基本sIB算法调用次数相同的条件下，isIB算法相对于sIB算法具有运行效率高、解更优化的特点．

英文摘要：

IB method employs the joint probability distribution between the source variable and the relevant variable to maximally compress the source variable, such that the middle compression variable can maximally save the information about the relevant variable. As a result, this method gives birth to several effective iterative algorithms, in which, the sequential IB algorithm （slB） is one of the better and widely applied IB algorithms. But this algorithm also has some limits, such as, low efficiency and insufficient optimization, etc. For the sake of solving these problems of the slB algorithm discovered in applications, an iterative slB algorithm （islB） based on mutation method is proposed here. Firstly, relevant experiments for selecting reasonable mutation rate are conducted. Based on this rate, the islB algorithm chooses random proportional positions from the initial solution vector resulting from a seeding slB algorithm, and randomly mutates the corresponding mapping relation from these chosen positions to the clustering labels. After getting the initial solution, the islB algorithm optimizes it iteratively. The experimental results on the benchmark data sets indicate that the proposed isIB algorithm outperforms the sIB algorithm in both the accuracy and the efficiency.