ICA Using Spacings Estimates of Entropy
ICA Using Spacings Estimates of Entropy
复制标题
DOI：
10.1162/jmlr.2003.4.7-8.1271
复制
发表时间：
2003-12
期刊：
影响因子：
--
通讯作者：
E. Learned-Miller;John W. Fisher III
中科院分区：
文献类型：
--
作者：
E. Learned-Miller;John W. Fisher III
提出了一种基于有效的熵估计的独立分量分析(ICA)问题的新算法。与许多以前的方法一样，该算法直接根据联合分布和边缘分布的乘积之间的估计Kullback-Leibler散度来最小化独立的度量。我们将这种方法与统计文献中的有效熵估计器配对。特别是，我们使用的熵估计器是一致的，并且表现出快速的收敛。基于该估计器的算法简单，计算效率高，具有直观的吸引力，性能优于其他知名算法。此外，估计器对异常值的相对不敏感性转化为我们的ICA算法在异常值测试中的卓越性能。在大量的仿真中，我们给出了与Kernel ICA、FAST-ICA、JADE和扩展的Infomax算法的有利比较。我们还为我们的算法提供了公共领域的源代码。
This paper presents a new algorithm for the independent components analysis (ICA) problem based on an efficient entropy estimator. Like many previous methods, this algorithm directly minimizes the measure of departure from independence according to the estimated Kullback-Leibler divergence between the joint distribution and the product of the marginal distributions. We pair this approach with efficient entropy estimators from the statistics literature. In particular, the entropy estimator we use is consistent and exhibits rapid convergence. The algorithm based on this estimator is simple, computationally efficient, intuitively appealing, and outperforms other well known algorithms. In addition, the estimator's relative insensitivity to outliers translates into superior performance by our ICA algorithm on outlier tests. We present favorable comparisons to the Kernel ICA, FAST-ICA, JADE, and extended Infomax algorithms in extensive simulations. We also provide public domain source code for our algorithms.