资源分类
》 资源 》论文》Exponential Concentration of a Density Functional Estimator

Exponential Concentration of a Density Functional Estimator

2020-01-19 | |  53 |   33 |   0

Abstract

We analyze a plug-in estimator for a large class of integral functionals of one or more continuous probability densities. This class includes important families of entropy, divergence, mutual information, and their conditional versions. For densities on the d-dimensional unit cube [0, 1]d that lie  in a 图片.png-Holder  smoothness  class, we prove our estimator converges at the rate 图片.png . Furthermore, we prove the estimator is exponentially concentrated about its mean, whereas most previous related results have proven only expected error bounds on estimators.

上一篇：Local Linear Convergence of Forward–Backward under Partial Smoothness

下一篇：Multi-Scale Spectral Decomposition of Massive Graphs

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...