Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators.
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016)(2016)
摘要
We provide finite-sample analysis of a general framework for using k-nearest neighbor statistics to estimate functionals of a nonparametric continuous probability density, including entropies and divergences. Rather than plugging a consistent density estimate (which requires k -> infinity as the sample size n -> infinity) into the functional of interest, the estimators we consider fix k and perform a bias correction. This is more efficient computationally, and, as we show in certain cases, statistically, leading to faster convergence rates. Our framework unifies several previous estimators, for most of which ours are the first finite sample guarantees.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络