0


关于α分歧的估计

On the Estimation of alpha-Divergences
课程网址: http://videolectures.net/aistats2011_poczes_estimation/  
主讲教师: Barnabás Póczos
开课单位: 卡内基梅隆大学
开课时间: 信息不详。欢迎您在右侧留言补充。
课程语种: 英语
中文简介:
针对连续分布,我们提出了新的非参数一致的renyi和tsallis散度估计器。给定两个独立且相同分布的样本,一种“朴素”的方法是简单地估计潜在密度,并将估计密度插入到相应的公式中。相比之下,我们提出的估计器完全避免了密度估计,只使用简单的k-最近邻统计数据直接估计差异。尽管如此,我们还是能够证明估计量在某些条件下是一致的。我们还描述了如何将这些估计应用于互信息,并通过数值实验证明了它们的有效性。
课程简介: We propose new nonparametric, consistent Renyi-alpha and Tsallis-alpha divergence estimators for continuous distributions. Given two independent and identically distributed samples, a ``naive'' approach would be to simply estimate the underlying densities and plug the estimated densities into the corresponding formulas. Our proposed estimators, in contrast, avoid density estimation completely, estimating the divergences directly using only simple k-nearest-neighbor statistics. We are nonetheless able to prove that the estimators are consistent under certain conditions. We also describe how to apply these estimators to mutual information and demonstrate their efficiency via numerical experiments.
关 键 词: α分歧; 估计
课程来源: 视频讲座网
最后编审: 2019-10-30:cwx
阅读次数: 13