arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1003.1954stat.MLcs.AI
收藏

基于广义近邻图的Rényi熵和互信息估计

Estimation of Rényi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs

University of Alberta(阿尔伯塔大学);Carnegie Mellon University(卡内基梅隆大学)

Dávid Pál, Barnabás Póczos, Csaba Szepesvári

摘要:

我们提出了简单和计算效率的非参数估计的Rényi熵和互信息的基础上的i.i.d.从$\R^d$上的未知绝对连续分布中抽取的样本。估计量分别计算为样本的“广义最近邻”图和样本的经验copula的边的欧几里得长度的$p$次幂之和。对于第一次,我们证明了几乎肯定的一致性,这些估计和上界的收敛速度,后者的假设下,密度的样本是Lipschitz连续的。实验证明了它们在独立子空间分析中的实用性。

英文摘要:

We present simple and computationally efficient nonparametric estimators of Rényi entropy and mutual information based on an i.i.d. sample drawn from an unknown, absolutely continuous distribution over $\R^d$. The estimators are calculated as the sum of $p$-th powers of the Euclidean lengths of the edges of the `generalized nearest-neighbor' graph of the sample and the empirical copula of the sample respectively. For the first time, we prove the almost sure consistency of these estimators and upper bounds on their rates of convergence, the latter of which under the assumption that the density underlying the sample is Lipschitz continuous. Experiments demonstrate their usefulness in independent subspace analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑